msv-2009.1/ 0000755 0001750 0001750 00000000000 11622453141 012617 5 ustar giovanni giovanni msv-2009.1/testharness/ 0000755 0001750 0001750 00000000000 11622453066 015170 5 ustar giovanni giovanni msv-2009.1/testharness/pom.xml 0000644 0001750 0001750 00000002322 11213776216 016505 0 ustar giovanni giovanni
4.0.0net.java.dev.msvmsv-testharness2009.1MSV Test Harnessnet.java.dev.msvmsv-parent2009.1../parent/pom.xmlscm:svn:http://msv.dev.java.net/svn/msv/tags/msv-2009.1/testharnessscm:svn:https://msv.dev.java.net/svn/msv/tags/msv-2009.1/testharnessxercesxercesImpljunitjunittestorg.apache.antant
msv-2009.1/testharness/build.xml 0000644 0001750 0001750 00000000735 10470130726 017011 0 ustar giovanni giovanni
msv-2009.1/testharness/examples/ 0000755 0001750 0001750 00000000000 11622453066 017006 5 ustar giovanni giovanni msv-2009.1/testharness/examples/example.rts 0000644 0001750 0001750 00000003600 07327417373 021202 0 ustar giovanni giovanni
Sun MicrosystemsSample test suite to test the harness codeKohsuke KAWAGUCHI$Id: example.rts 954 2001-07-25 01:20:59Z Bear $
Does the processor support W3C XML Schema as a datatype library?
5 -52 abc msv-2009.1/testharness/doc/ 0000755 0001750 0001750 00000000000 11622453066 015735 5 ustar giovanni giovanni msv-2009.1/testharness/doc/testSuite.rng 0000644 0001750 0001750 00000010112 07365140104 020424 0 ustar giovanni giovanni
okng
[-A-Za-z0-9:@&=+$,_.!~*'()]+
msv-2009.1/testharness/doc/BSD License.txt 0000644 0001750 0001750 00000002745 07327415040 020456 0 ustar giovanni giovanni Copyright (c) 2001, Sun Microsystems, Inc.
All rights reserved.
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions
are met:
* Redistributions of source code must retain the above copyright
notice, this list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above copyright
notice, this list of conditions and the following disclaimer in
the documentation and/or other materials provided with the
distribution.
* Neither the name of Sun Microsystems, Inc. nor the names of its
contributors may be used to endorse or promote products derived
from this software without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL
THE COPYRIGHT HOLDERS OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT,
INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
(INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION
HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT,
STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF
ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
msv-2009.1/testharness/doc/readme.txt 0000644 0001750 0001750 00000004357 07331355534 017747 0 ustar giovanni giovanni ======================================================================
README FILE FOR RELAX NG CONFORMANCE TEST HARNESS FOR JAVA
Copyright (c) Sun Microsystems, 2001
Document by Kohsuke Kawaguchi (kohsuke.kawaguchi@sun.com)
$Revision: 987 $
======================================================================
RELAX NG Conformance Test Harness for Java is an Open-source Java
framework to test the conformance of RELAX NG processors.
----------------------------------------------------------------------
OVERVIEW
----------------------------------------------------------------------
This framework parses the test suite files and then use JUnit to test
RELAX NG processor. So first you need a test suite file.
See the examples folder of the distribution and "testSuite.rng" file
for how to write a test suite file.
Then, you need a RELAX NG processor and a driver implementation for
that processor. The driver impl for Sun Multi-Schema Validator is
included as "msvDriver.jar" in the distribution. See javadoc for
how to implement a driver for arbitrary RELAX NG processors.
To run a test, enter the following command:
$ java -jar rngtsth.jar ...
For example, to test the conformance of MSV with foo.rts and bar.rts,
$ java -jar rngtsth.jar jing.IValidatorImpl foo.rts bar.rts
Your classpath must include junit.jar, msv.jar and msvDriver.jar.
----------------------------------------------------------------------
WRITING AN ADAPTOR
----------------------------------------------------------------------
This framework provides the core functionality to parse test suite
files and perform tests by them. However, to use this framework with
your own RELAX NG processor, you need to write an "driver", which
bridges the framework and the processor.
To implement a driver, you need to write two classes that implements
the org.relaxng.testharness.validator.IValidator interface and
the org.relaxng.testharness.validator.ISchema interface.
See msvDriver-src.zip for an example. It should be easy if the processor
supports SAX or DOM based input.
======================================================================
END OF README
msv-2009.1/testharness/MANIFEST.MF 0000644 0001750 0001750 00000000166 07327415311 016623 0 ustar giovanni giovanni Manifest-Version: 1.0
Main-Class: org.relaxng.testharness.junit.TestRunner
Created-By: 1.2.2 (Sun Microsystems Inc.)
msv-2009.1/testharness/src/ 0000755 0001750 0001750 00000000000 11622453066 015757 5 ustar giovanni giovanni msv-2009.1/testharness/src/SAXONLiaison.java 0000644 0001750 0001750 00000007266 11156723336 021046 0 ustar giovanni giovanni /*
* @(#)$Id: SAXONLiaison.java 1741 2009-03-14 12:45:18Z bimargulies $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
import javax.xml.transform.*;
import javax.xml.transform.stream.StreamSource;
import javax.xml.transform.stream.StreamResult;
import java.io.File;
import java.io.FileInputStream;
import java.io.FileOutputStream;
import java.io.IOException;
/**
* XSLTLiaison implementation for SAXON.
*
* This doesn't use Saxon any longer. It uses the JDK TraX.
*
*
* This class
*/
public class SAXONLiaison implements org.apache.tools.ant.taskdefs.XSLTLiaison
{
/** The trax TransformerFactory */
private TransformerFactory tfactory = null;
/** stylesheet stream, close it asap */
private FileInputStream xslStream = null;
/** Stylesheet template */
private Templates templates = null;
/** transformer */
private Transformer transformer = null;
public SAXONLiaison() throws Exception {
tfactory = TransformerFactory.newInstance();
}
//------------------- IMPORTANT
// 1) Don't use the StreamSource(File) ctor. It won't work with
// xalan prior to 2.2 because of systemid bugs.
// 2) Use a stream so that you can close it yourself quickly
// and avoid keeping the handle until the object is garbaged.
// (always keep control), otherwise you won't be able to delete
// the file quickly on windows.
// 3) Always set the systemid to the source for imports, includes...
// in xsl and xml...
public void setStylesheet(File stylesheet) throws Exception {
xslStream = new FileInputStream(stylesheet);
StreamSource src = new StreamSource(xslStream);
src.setSystemId(getSystemId(stylesheet));
templates = tfactory.newTemplates(src);
transformer = templates.newTransformer();
}
public void transform(File infile, File outfile) throws Exception {
FileInputStream fis = null;
FileOutputStream fos = null;
try {
fis = new FileInputStream(infile);
fos = new FileOutputStream(outfile);
StreamSource src = new StreamSource(fis);
src.setSystemId(getSystemId(infile));
StreamResult res = new StreamResult(fos);
// not sure what could be the need of this...
res.setSystemId(getSystemId(outfile));
transformer.transform(src, res);
} finally {
// make sure to close all handles, otherwise the garbage
// collector will close them...whenever possible and
// Windows may complain about not being able to delete files.
try {
if (xslStream != null){
xslStream.close();
}
} catch (IOException ignored){}
try {
if (fis != null){
fis.close();
}
} catch (IOException ignored){}
try {
if (fos != null){
fos.close();
}
} catch (IOException ignored){}
}
}
// make sure that the systemid is made of '/' and not '\' otherwise
// crimson will complain that it cannot resolve relative entities
// because it grabs the base uri via lastIndexOf('/') without
// making sure it is really a /'ed path
protected String getSystemId(File file){
String path = file.getAbsolutePath();
path = path.replace('\\','/');
return FILE_PROTOCOL_PREFIX + path;
}
public void addParam(String name, String value){
transformer.setParameter(name, value);
}
} msv-2009.1/testharness/src/PathExtractor.java 0000644 0001750 0001750 00000001113 07410436423 021404 0 ustar giovanni giovanni import java.io.File;
/**
* Extracts the path part from "file://" URL.
*
* For example, extract("file://home/abc/def/ghi.xml")
* returns "/home/abc/def/ghi"
*/
public class PathExtractor {
public static String extract( String uri ) {
String path = uri.substring(5); // file:
int idx = path.lastIndexOf('.');
path = path.substring(0,idx);
if (File.separatorChar == '\\') {
path = path.replace('/', '\\');
while(path.charAt(0)=='\\')
path = path.substring(1);
} else {
while(path.startsWith("//"))
path = path.substring(1);
}
return path;
}
} msv-2009.1/pom.xml 0000644 0001750 0001750 00000022516 11213776216 014151 0 ustar giovanni giovanni
4.0.0net.java.dev.msvmsv2009.1msvhttp://msv.java.netpomscm:svn:http://msv.dev.java.net/svn/msv/tags/msv-2009.1scm:svn:https://msv.dev.java.net/svn/msv/tags/msv-2009.12.0.8falseBSDrepoparentxsdlibtestharnessmsvgeneratorrngconverterdeploydeployorg.apache.maven.pluginsmaven-source-plugin2.0.4attach-sourcesjarorg.apache.maven.pluginsmaven-javadoc-pluginattach-javadocsjarinstallorg.codehaus.mojobuild-helper-maven-plugin1.2org.apache.felixmaven-bundle-plugin1.4.3org.apache.maven.pluginsmaven-release-plugin2.0-beta-9https://msv.dev.java.net/svn/msv/tagsfalseclean installdeploy-Pdeploytrueorg.apache.maven.pluginsmaven-javadoc-plugin2.5true1.5trueMSV1.5UTF-8org.apache.maven.pluginsmaven-surefire-plugin2.4.3org.apache.maven.pluginsmaven-compiler-plugin2.0.21.51.5256M${compiler.fork}org.apache.maven.pluginsmaven-antrun-plugin1.2org.apache.maven.pluginsmaven-jar-plugin2.2org.apache.maven.pluginsmaven-resources-plugin2.2org.apache.maven.pluginsmaven-assembly-plugin2.2-beta-2org.apache.maven.pluginsmaven-dependency-plugin2.0org.apache.maven.pluginsmaven-eclipse-plugin2.5.1org.jvnet.wagon-svnwagon-svn1.8org.apache.maven.pluginsmaven-project-info-reports-pluginorg.apache.maven.pluginsmaven-javadoc-plugin2.2truetruemaven2-repository.dev.java.netJava.net Repository for Mavenhttp://download.java.net/maven/2/falsejava.net-maven2-repositoryjava-net:/maven2-repository/trunk/repository/
msv-2009.1/www/ 0000755 0001750 0001750 00000000000 11622453065 013450 5 ustar giovanni giovanni msv-2009.1/www/alm-process/ 0000755 0001750 0001750 00000000000 11622453065 015675 5 ustar giovanni giovanni msv-2009.1/www/alm-process/snippets/ 0000755 0001750 0001750 00000000000 11622453065 017542 5 ustar giovanni giovanni msv-2009.1/www/alm-process/snippets/page.xml 0000644 0001750 0001750 00000000665 11156245242 021205 0 ustar giovanni giovanni
index.htmlSubprojects
msv-2009.1/www/xss.html 0000644 0001750 0001750 00000000170 07676612160 015160 0 ustar giovanni giovanni
XSS vulnerability test.
msv-2009.1/www/index.html 0000644 0001750 0001750 00000002354 10736744756 015470 0 ustar giovanni giovanni
The Sun Multi-Schema XML Validator (MSV) is a Java technology tool to validate XML documents against several kinds of XML schemata. It supports RELAX NG, RELAX Namespace, RELAX Core, TREX, XML DTDs, and a subset of XML Schema Part 1. This latest (version 1.2) release includes several bug fixes and adds better conformance to RELAX NG/W3C XML standards and JAXP masquerading. This download package includes binaries, source code, and detailed documentation. The project is licensed under the BSD license.
This tool is:
A command line tool that can read XML documents and validate them against a schema (DTD/RELAX/TREX/W3C). If an error is found, error messages are provided.
A library that can be incorporated into Java applications as a validator.
See the included commandline.html file for details on how to use MSV from the command line. See the included developer.html file for details on how to use it as a library.
msv-2009.1/tahiti/test/ 0000755 0001750 0001750 00000000000 11622453065 015065 5 ustar giovanni giovanni msv-2009.1/tahiti/test/TestDriver.java 0000644 0001750 0001750 00000002676 07326165653 020047 0 ustar giovanni giovanni import com.sun.msv.grammar.Grammar;
import com.sun.tahiti.runtime.ll.*;
import com.sun.tahiti.runtime.sm.*;
import javax.xml.parsers.SAXParserFactory;
import org.xml.sax.XMLReader;
import org.xml.sax.SAXException;
public class TestDriver
{
public static void main( String args[] ) throws Exception {
if( args.length!=2 ) {
System.out.println(
"Usage: TestDriver \n"+
" This test driver uses the specified grammar to \n"+
" parse the specified instance.");
return;
}
SAXParserFactory factory = new org.apache.xerces.jaxp.SAXParserFactoryImpl();
factory.setNamespaceAware(true);
System.out.println("preparing a grammar");
long cnt = System.currentTimeMillis();
Unmarshaller unmarshaller = new Unmarshaller( getGrammar(args[0]) );
System.out.println("preparation complete: ("+(System.currentTimeMillis()-cnt)+"ms)");
XMLReader reader = factory.newSAXParser().getXMLReader();
reader.setContentHandler(unmarshaller);
try {
reader.parse(args[1]);
} catch( SAXException e ) {
if( e.getException()!=null )
e.getException().printStackTrace();
}
MarshallableObject mo = unmarshaller.getResult();
System.out.println(mo);
// serialize
MarshallerAPI.marshall( mo, System.out, "UTF-8", true );
}
static BindableGrammar getGrammar( String className ) throws Exception {
return (BindableGrammar)Class.forName(className).getField("grammar").get(null);
}
}
msv-2009.1/tahiti/test/Driver.java 0000644 0001750 0001750 00000000204 07317145253 017162 0 ustar giovanni giovanni
public class Driver {
public static void main(String[] args) throws Exception {
com.sun.tahiti.compiler.Driver.main(args);
}
}
msv-2009.1/tahiti/doc/ 0000755 0001750 0001750 00000000000 11622453065 014653 5 ustar giovanni giovanni msv-2009.1/tahiti/doc/UsersGuide.docbook 0000644 0001750 0001750 00000012066 07326165745 020314 0 ustar giovanni giovanni
$Id: UsersGuide.docbook 935 2001-07-21 02:41:41Z Bear $Tahiti User's GuideKAWAGUCHIKohsukekohsuke.kawaguchi@sun.com2001Sun Microsystems
Sun internal use only.
This document describes the general usage of Tahiti.
Getting Started
First, you need a grammar. Tahiti supports various schema language,
but let's assume you have "foo.rng" file as your grammar.
Then the first thing you should do is to run the schema compiler.
java -jar tahiti.jar foo.rng]]>
Schema compiler will generate Java source codes to the current directory.
If you want it to place those files to another directory, then you can use
the -d option like this:
java Compiler foo.rng -d ../../src]]>
Although the compiler takes every effort to extract a meaningful mapping from the schema,
often it falls short of your expectation.
If that is the case, you can control the way
the compiler maps schemas to Java classes
by annotating schema files.
The annotation depends on the schema language you use. Consult the documentation
for your choice of the schema language.
RELAX NG annotation
Using the generated classes
This section describes how you can use the genrated Java classes to do what you want.
You should know two important operations involving the generated classes.
One is marshalling and the other is
unmarshallingUnmarshalling
Unmarshalling is the process that reads an XML document and creates the corresponding
Java objects. The easiest way to do this is to do as follows:
The above method will read the document from the specified location and returns
the result.
org.example.test.Grammar is the name of
the compiled grammar, which is generated by the schema compiler.
You should replace it with appropriate class name.
There are severl other overloaded version of this method, which accepts
various type of inputs like
org.xml.sax.InputSource or
java.io.InputStream.
Should any error happens during the process of unmarshalling, an exception
is thrown. See javadoc for details.
Marshalling
Marshalling is the process that writes XML representation of the Java object model.
The easiest way to do this is to use the MarshallerAPI
class.
This class lets you produce XML in many ways.
There are handful of overloaded versions of the marshall method, each support
different type of output.
Unfortunately, the implementation of the marshaller is rather poor at this moment.
Sometimes, the compiler fails to produce a marshaller for a grammar.
If it fails, please let us know so that we invent a better algorithm.
Also, there is a workaround. If the compiler fails to produce a marshaller,
then you can derive that class and implement it by hand.
Creating objects programatically
Unmarshalling is not the only way to construct an object model.
Instead, you can programatically create it from scratch, much like
you can create a DOM tree from scratch by using the createXXX methods
of a org.w3c.dom.Document object.
msv-2009.1/tahiti/doc/copyright.txt 0000644 0001750 0001750 00000005243 07326115717 017435 0 ustar giovanni giovanni Copyright 2001 Sun Microsystems, Inc. 901 San Antonio Road, Palo Alto,
California, 94303, U.S.A. All rights reserved.
Sun Microsystems, Inc. has intellectual property rights relating to
technology embodied in this product. In particular, and without
limitation, these intellectual property rights may include one or more
of the U.S. patents listed at http://www.sun.com/patents and one or
more additional patents or pending patent applications in the U.S. and
other countries. This product is distributed under licenses
restricting its use, copying, distribution, and decompilation. No part
of this product may be reproduced in any form by any means without
prior written authorization of Sun and its licensors, if any. Third
party software, including font technology, is copyrighted and licensed
from Sun suppliers. Sun, the Sun logo, and Sun Microsystems are
trademarks or registered trademarks of Sun Microsystems, Inc. in the
U.S. and other countries. This product includes software developed by
the Apache Software Foundation (http://www.apache.org/). Federal
Acquisitions: Commercial Software - Government Users Subject to
Standard License Terms and Conditions.
----------------------------------------------------------------------
Copyright 2001 Sun Microsystems, Inc., 901 San Antonio Road, Palo
Alto, Californie 94303 États-Unis. Tous droits réservés. Distribueé
par des licences qui en restreignent l'utilisation. Sun Microsystems,
Inc. a les droits de propriété intellectuels relatants à la
technologie incorporée dans ce produit. En particulier, et sans la
limitation, ces droits de propriété intellectuels peuvent inclure un
ou plus des brevets américains énumérés à http://www.sun.com/patents
et un ou les brevets plus supplémentaires ou les applications de
brevet en attente dans les Etats Unis et les autres pays. Ce produit
ou document est protégé par un copyright et distribué avec des
licences qui en restreignent l'utilisation, la copie, la distribution,
et la décompilation. Aucune partie de ce produit ou document ne peut
être reproduite sous aucune forme, par quelque moyen que ce soit, sans
l'autorisation préalable et écrite de Sun et de ses bailleurs de
licence, s'il y en a. Le logiciel détenu par des tiers, et qui
comprend la technologie relative aux polices de caractères, est
protégé par un copyright et licencié par des fournisseurs de Sun. Sun,
le logo Sun, Sun Microsystems et sont des marques de fabrique ou des
marques d?pos?es de Sun Microsystems, Inc. aux Etats-Unis et dans
d'autres pays. Ce produit inclut le logiciel développé par la base de
Apache Software Foundation (http://www.apache.org/). L'accord du
gouvernement des États Unis est requis avant l'exportation du produit.
msv-2009.1/tahiti/doc/tahiti.xsl 0000644 0001750 0001750 00000001501 07326121265 016662 0 ustar giovanni giovanni
tahiti.css
[]
msv-2009.1/tahiti/doc/Apache-LICENSE-1.1.txt 0000644 0001750 0001750 00000005413 07326115717 020162 0 ustar giovanni giovanni /* ====================================================================
* The Apache Software License, Version 1.1
*
* Copyright (c) 2000 The Apache Software Foundation. All rights
* reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
*
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
*
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in
* the documentation and/or other materials provided with the
* distribution.
*
* 3. The end-user documentation included with the redistribution,
* if any, must include the following acknowledgment:
* "This product includes software developed by the
* Apache Software Foundation (http://www.apache.org/)."
* Alternately, this acknowledgment may appear in the software itself,
* if and wherever such third-party acknowledgments normally appear.
*
* 4. The names "Apache" and "Apache Software Foundation" must
* not be used to endorse or promote products derived from this
* software without prior written permission. For written
* permission, please contact apache@apache.org.
*
* 5. Products derived from this software may not be called "Apache",
* nor may "Apache" appear in their name, without prior written
* permission of the Apache Software Foundation.
*
* THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESSED OR IMPLIED
* WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
* OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
* DISCLAIMED. IN NO EVENT SHALL THE APACHE SOFTWARE FOUNDATION OR
* ITS CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
* SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
* LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF
* USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
* ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
* OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT
* OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
* SUCH DAMAGE.
* ====================================================================
*
* This software consists of voluntary contributions made by many
* individuals on behalf of the Apache Software Foundation. For more
* information on the Apache Software Foundation, please see
* .
*
* Portions of this software are based upon public domain software
* originally written at the National Center for Supercomputing Applications,
* University of Illinois, Urbana-Champaign.
*/
msv-2009.1/tahiti/doc/README.txt 0000644 0001750 0001750 00000002540 07334547665 016371 0 ustar giovanni giovanni ======================================================================
README FILE FOR "TAHITI"
Preview Version July, 2001
Copyright (c) Sun Microsystems, 2001
Document written by Kohsuke Kawaguchi (kohsuke.kawaguchi@sun.com)
$Revision: 1058 $
======================================================================
"Tahiti" is a Java tool to generate a Java object model from a schema.
Currently, it supports RELAX NG.
This release includes software developed by the Apache Software
Foundation (http://xml.apache.org/).
----------------------------------------------------------------------
OVERVIEW
----------------------------------------------------------------------
This tool is a command line tool that can compile RELAX NG grammar to
a Java object model that in turn parses XML documents written in that
schema.
The automatic Java object model generation makes it easy to read/write
XML documents from your application. Also, This tool lets you heavily
customize the generated object model.
See UsersGuide.html for details.
This tool should be considered as alpha-quality. And any feedback is
more than welcome! Please send it to kohsuke.kawaguchi@sun.com
======================================================================
END OF README
msv-2009.1/tahiti/doc/RELAX NG Bind.docbook 0000644 0001750 0001750 00000050245 07326165745 020233 0 ustar giovanni giovanni
$Id: RELAX NG Bind.docbook 935 2001-07-21 02:41:41Z Bear $Tahiti User's Guide for RELAX NGKAWAGUCHIKohsukekohsuke.kawaguchi@eng.sun.com2001Sun Microsystems
Sun internal use only.
This document describes how to use Tahiti with RELAX NG.
Control the compiler
Although the compiler takes every effort to extract a meaningful mapping from the schema,
but often it is not wise enough.
By annotating schema files, you can control the way
the compiler maps schemas to Java classes.
Tahiti defines a set of global attributes to annotate RELAX NG schema, just like XLink does.
All the attributes are placed in the http://www.sun.com/xml/tahiti/
namespace.
Tahiti defines only three attributes.
Tahiti annotation attributesNameTypeMeaningroleclass/interface/field/superClass/none/ignore
it controls how a RELAX NG pattern will be mapped to a Java item.
nameJava identifier name
it provides a hint to the compiler about the identifier it should use.
(e.g., class name, field name, etc.)
packageJava package name
It specified the package name in which the generated classes will reside.
This field should be something like "org.example.foo".
The following sections will guide you through each attributes and how you can use them
to obtain what you want.
The role attribute
The role attribute is the most important annotation. It controls how RELAX NG grammar
should be mapped to a Java item.
The value of the role attribute can be one of "class","interface","field","superClass","none",
and "ignore".
"none" - Suppress unnecessary classesrole="none" is an instruction to the compiler
not to generate a class for the particular pattern.
Since the compiler usually maps <element> patterns to Java classes,
role="none" is usually used on <element> patterns.
Sometimes the compiler generates Java classes that look unnecessary.
Consider the following grammar:
t:role="none"
]]>
Without the role attribute,
The compiler will generate one Java class for the "info" element, and another one
for the "header" element.
By specifying the role attribute as none, the compiler will suppress a Java class
for the "info" element. As a result, the Header class will have the author field
and the version field.
"ignore" - Ignore a part of the documentrole="ignore" is an instruction to the compiler to
ignore the specified part of the grammar.
Many vocabularies (e.g., RELAX NG, W3C XML Schema) allows their
instances to be annotated by attributes from other namespaces.
Many grammars also provides a place holder element inside which
elements from other namespaces can appear (e.g., <appInfo>
tag of W3C XML Schema).
For example, RELAX NG schema for RELAX NG has the following definition,
which allows any element of RELAX NG to have attributes from other namespaces.
....
t:role="ignore"
]]>
Without the role attribute, the compiler will create a class to capture each attribute from
foreign namespaces. But chances are, you don't care about those attributes.
With the role attribute as "ignore" on the zeroOrMore pattern, the generated
Java object model will ignore the entire descendants of that pattern. In this case,
this means that the all attributes from foreign namespaces are ignored.
The effect of role="ignore" is not affected by the <ref>
pattern. The following example will result in the object model that only cares
about the contents of the head tag (and ignores the entire contents of the body tag.)
t:role="ignore"
]]>"class" - Specifies a Java class
Sometimes, you want the compiler to map a certain pattern to a Java class.
role="class" is an instruction to the compiler to
generate a class for a particular pattern.
Consider the following example:
t:role="class" t:name="Length"mmmkm
]]>
The role attribute forces the compiler to create a Java
class, whose name "Length" is also specified by the name attribute.
The Length class will have two fields; one for the integer value and
another for the unit.
Note that in the above example, an otherwise unnecessary <group> pattern
is added so that the Tahiti attributes can creep in. If we specify the role attribute
on the zeroOrMore pattern, then the class will be generated for the entire list of
distances, not for one distance.
As done in the above example, sometimes you may want to modify a schema
a bit so that you can annotate it in the way you want.
"field" - Specifies a fieldrole="field" is an instruction to the compiler
to create a field and accomodate child objects into that field.
The primary use case of this instruction is to change the way fields
are created. Consider the following example:
]]>
This is a (slightly modified) fragment of the RELAX NG schema for RELAX NG.
Let's assume that the compiler will generate four classes. The Grammar class
for the grammar element, the Start class for the start element, the Define class
for the define element, and finally the Include class for the include element.
Since the content model of the grammar element is zero-or-more-ed choice of
three elements, the compiler will generate one field for the Grammar class to store all three kinds of
objects created for child elements.
But in this case, you may want to have three fields: one for the Include class,
one for the Define class, and one for the Start class. To do this, use
role="field" as follows:
t:role="field" t:name="starts"t:role="field" t:name="defines"t:role="field" t:name="includes"
]]>
In this way, three fields ("starts","defines", and "includes") are created for each child classes.
The starts field will receive objects of the Start class, so on, so forth.
You can specify the same name for multiple role="field" declaration.
In RELAX NG, the start pattern and the define pattern is very similar. The following annotation
will generate two fields for the Grammar class.
t:role="field" t:name="defines"t:role="field" t:name="defines"
]]>
Now the defines field will receive instances of both the Define class and the Start class.
Take the opposite example. If you want to ensure that all three child classes are stored
into one field, then you can place the instruction to the choice pattern or the zeroOrMore pattern.
t:role="field" t:name="declarations"
]]>
It doesn't matter where you place the role="field" instruction, as long as
it is placed between the parent class and the child class.
"interface" - Specifies an interfacerole="interface" is an instruction to the compiler to generate
an interface and have designated classes implement that interface.
This is usually used in the choice pattern. Consider the following example:
t:role="interface" ... ... ...
]]>
By this instruction, the compiler will generate the InlineItem interface. This interface is
then implemented by the Bold class, the Span class, and the Font class.
As a result of this, the Foo class will get the following signature:
Once role="interface" is specified, then this interface will be
used throughout in the grammar. If there is a bar element like this:
... ...
]]>
Then the corresponding Bar class will also get the field of the InlineItem type.
role="interface" can be nested to create a hierarchy of interfaces.
t:role="interface" ... ... t:role="interface" ... ... t:role="interface"
]]>
In this way, you'll get the following type hierarchy.
"superClass" - Designates the super class
Tahiti allows you to specify the implementation inheritance by using role="superClass".
Since the extraction of this information is very difficult, the compiler will never
attempt to automatically detect the implementation inheritance relationships.
To designate the super class, place the role="superClass" instruction between
the derived class and the base class like this:
t:role="superClass"t:role="superClass"t:role="class"
]]>
The compiler will automatically generate the Add class and the Sub class.
And since their content model has the role="superClass" instruction,
the designated BinaryOperator class will be used as the super class of these two classes.
The following pattern will achieve the same result:
t:role="superClass"t:role="class"
]]>
As you see, there is no restriction about the place you can put
the role="superClass" instruction as long as
it is between the derived class and the base class.
However, there is one important restriction about the use of this instruction.
Intuitively, the derived class must always have one and only one instance of the base class.
Consider the following example:
t:role="superClass"t:role="class"
]]>
In this example, the Add class can contain more than one instance of the BinaryOperator classes.
Apparently, this doesn' match with the fact that the BinaryOperator class is the base class of the
Add class. The use of the role="superClass" instruction in this way is prohibited.
The name attribute
The name attribute is a supplementary instruction that gives the compiler the information about the name of
classes, interfaces, and fields.
As you have seen in the explanation of the role attribute, the name attribute is usually coupled with
the role attribute. But actually, the name attribute can be used by itself to specify the name for
classes and fields automatically generated by the compiler.
Let's consider the following example.
]]>
The compiler will find that this element should be mapped to a Java class.
Usually, this generated class will be named after the name of element/attribute names or
the nearest name specified for <define>. But in this particular case, there is no such hint.
To help the compiler, you can specify the name attribute on the element pattern.
t:name="Name"
]]>
In this way, the compiler will generate the Name class,
which will have the firstName field and the lastName field.
Similarly, the name attribute can be also used to rename the field name. For example, if you
want to have the given field and the family field, then you can do that by using
the name attribute.
t:name="Name"t:name="given"t:name="family"
]]>
This technique is also useful to solve the name collision to Java reserved names.
The package attribute
The package attribute is used to specify the package name in which the generated classes will be placed.
Usually, you want to place everything into one package. In that case, you should specify the package attribute
to the document element like this:
t:package="org.example.test"
....
]]>
All the classes generated from this grammar, including included grammars, will be placed into this package.
Actually, the package attribute can be specified anywhere in the grammar, as in the following example.
Once specified, it is effective on all descendants, unless a new package name is specified.
t:package="org.example.test"t:package="org.example.test.foo"t:package="com.abcdef.bar"
]]>
In the above example, the Root class will go to the "org.example.test" package,
the Sub1 class will go to the "org.example.test.foo" package, and
the Sub2 class will go to the "com.abcdef.bar" package.
msv-2009.1/tahiti/doc/tahiti.css 0000644 0001750 0001750 00000001426 07317204014 016644 0 ustar giovanni giovanni pre.programlisting {
margin-left: 2em;
margin-right: 2em;
padding: 1em;
font-weight: bold;
color: rgb(0,0,128);
background-image: url(figures/programListingEdge.gif);
background-position:top right;
background-repeat: no-repeat;
background-color: rgb(220,220,255);
}
pre.screen {
margin-left: 2em;
margin-right: 2em;
padding: 1em;
font-weight: bold;
color: rgb(0,0,0);
background-color: rgb(230,230,230);
}
div.mediaobject {
text-align: center;
}
h2 {
margin-top: 2em;
border-left: 0.5em solid navy;
border-right: 0.5em solid navy;
border-top: 1pt solid navy;
border-bottom: 1pt solid navy;
padding-left: 1em;
}
h3 {
margin-top: 1em;
border-bottom: 2pt double navy;
}
p {
margin-left: 1em;
}
div.footnote {
margin-top: 0.5em;
}
msv-2009.1/tahiti/doc/figures/ 0000755 0001750 0001750 00000000000 11622453065 016317 5 ustar giovanni giovanni msv-2009.1/tahiti/doc/figures/programListingEdge.gif 0000644 0001750 0001750 00000000100 07317204277 022570 0 ustar giovanni giovanni GIF89a € ÿÿÿÜÜÿ!ù , „ɱ|܃r¦j#n8w‡| ">%X ; msv-2009.1/tahiti/MANIFEST.MF 0000644 0001750 0001750 00000000247 07337343303 015544 0 ustar giovanni giovanni Manifest-Version: 1.0
Main-Class: com.sun.tahiti.compiler.Driver
Created-By: 1.2.2 (Sun Microsystems Inc.)
Class-path: xerces.jar xalan.jar msv.jar tahiti.runtime.jar
msv-2009.1/tahiti/src/ 0000755 0001750 0001750 00000000000 11622453065 014675 5 ustar giovanni giovanni msv-2009.1/tahiti/src/com/ 0000755 0001750 0001750 00000000000 11622453065 015453 5 ustar giovanni giovanni msv-2009.1/tahiti/src/com/sun/ 0000755 0001750 0001750 00000000000 11622453065 016260 5 ustar giovanni giovanni msv-2009.1/tahiti/src/com/sun/tahiti/ 0000755 0001750 0001750 00000000000 11622453065 017542 5 ustar giovanni giovanni msv-2009.1/tahiti/src/com/sun/tahiti/reader/ 0000755 0001750 0001750 00000000000 11622453065 021004 5 ustar giovanni giovanni msv-2009.1/tahiti/src/com/sun/tahiti/reader/TahitiGrammarReader.java 0000644 0001750 0001750 00000002071 07337072463 025532 0 ustar giovanni giovanni /*
* @(#)$Id: TahitiGrammarReader.java 1081 2001-08-17 01:36:51Z Bear $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.tahiti.reader;
import com.sun.tahiti.grammar.AnnotatedGrammar;
/**
* Base interface that must be implemented by any GrammarReader
* that can construct Tahiti-annotated AGM.
*
* @author
* Kohsuke KAWAGUCHI
*/
public interface TahitiGrammarReader
{
public static final String TahitiNamespace =
"http://www.sun.com/xml/tahiti/";
/**
* the same as the getResult method, but this one returns
* an AnnotatedGrammar object.
*/
AnnotatedGrammar getAnnotatedResult();
public static final String ERR_INVALID_COLLECTION_TYPE = // arg:1
"InvalidCollectionType";
public static final String ERR_INVALID_ACCESS_MODIFIER = // arg:1
"InvalidAccessModifier";
public static final String ERR_INVALID_ACCESSOR = // arg:1
"InvalidAccessor";
}
msv-2009.1/tahiti/src/com/sun/tahiti/reader/GrammarLoader.java 0000644 0001750 0001750 00000007573 07363143557 024411 0 ustar giovanni giovanni /*
* @(#)$Id: GrammarLoader.java 1231 2001-10-16 23:49:03Z Bear $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.tahiti.reader;
import com.sun.tahiti.grammar.AnnotatedGrammar;
import com.sun.tahiti.reader.relaxng.TRELAXNGReader;
import com.sun.tahiti.reader.xmlschema.TXMLSchemaReader;
import com.sun.msv.reader.GrammarReader;
import com.sun.msv.reader.GrammarReaderController;
import com.sun.msv.reader.util.ForkContentHandler;
import com.sun.msv.reader.util.GrammarReaderControllerAdaptor;
import org.xml.sax.*;
import org.xml.sax.helpers.DefaultHandler;
import java.util.Vector;
import javax.xml.parsers.SAXParserFactory;
import javax.xml.parsers.ParserConfigurationException;
/**
* loads Tahiti-annotated grammar
* by automatically detecting the language used.
*
* @author Kohsuke KAWAGUCHI
*/
public class GrammarLoader {
/**
* returns the parsed grammar, or null otherwise.
*/
public static AnnotatedGrammar loadSchema( String url,
GrammarReaderController controller,
SAXParserFactory factory )
throws SAXException, ParserConfigurationException, java.io.IOException
{
return _loadSchema(url,controller,factory);
}
/**
* returns the parsed grammar, or null otherwise.
*/
public static AnnotatedGrammar loadSchema( InputSource source,
GrammarReaderController controller,
SAXParserFactory factory )
throws SAXException, ParserConfigurationException, java.io.IOException
{
return _loadSchema(source,controller,factory);
}
/**
* returns the parsed grammar, or null otherwise.
*/
public static AnnotatedGrammar loadSchema( String source,
GrammarReaderController controller )
throws SAXException, ParserConfigurationException, java.io.IOException
{
SAXParserFactory factory = SAXParserFactory.newInstance();
factory.setNamespaceAware(true);
return _loadSchema(source,controller,factory);
}
private static AnnotatedGrammar _loadSchema( Object source,
final GrammarReaderController controller,
SAXParserFactory factory )
throws SAXException, ParserConfigurationException, java.io.IOException
{
final TRELAXNGReader relaxNg = new TRELAXNGReader(controller,factory);
final TXMLSchemaReader xmlSchema = new TXMLSchemaReader(controller,factory);
final XMLReader parser = factory.newSAXParser().getXMLReader();
final GrammarReader[] winner = new GrammarReader[1];
parser.setContentHandler( new DefaultHandler() {
private Locator locator;
private Vector prefixes = new Vector();
public void setDocumentLocator( Locator loc ) {
this.locator = loc;
}
public void startPrefixMapping( String prefix, String uri ) {
prefixes.add( new String[]{prefix,uri} );
}
public void startElement( String namespaceURI, String localName, String qName, Attributes atts )
throws SAXException {
if( localName.equals("schema") )
winner[0] = xmlSchema; // assume XML Schema
else
winner[0] = relaxNg;
// simulate the start of the document.
winner[0].setDocumentLocator(locator);
winner[0].startDocument();
for( int i=0; iKohsuke KAWAGUCHI
*/
public class TypeUtil {
/**
* compute the common base type of types.
*
* TODO: this is a very interesting problem. Since one type has possibly
* multiple base types, it's not an easy problem.
* The current implementation is very naive.
*/
public static Type getCommonBaseType( Type[] t ) {
// TODO:
for( int i=1; iKohsuke KAWAGUCHI
*/
public class Annotator
{
private static java.io.PrintStream debug = System.out;
public static Expression annotate( AnnotatedGrammar grammar, GrammarReader reader ) {
ClassItem[] classes;
/*
remove from the grammar. affects the
calculation of multiplicity and therefore has to be removed first.
*/
{
if(debug!=null) debug.println("removing notAllowed");
NotAllowedRemover visitor = new NotAllowedRemover(grammar.getPool());
grammar.topLevel = grammar.topLevel.visit( visitor );
if( grammar.topLevel==Expression.nullSet ) return Expression.nullSet;
// abstract elements of XSD makes AGM disjoint.
// so we have to explicitly visit each children.
classes = grammar.getClasses();
for( int i=0; is.
*/
if(debug!=null) debug.println("annotating complex choices");
ChoiceAnnotator.annotate( grammar );
/*
then remove temporarily added class items. temporary class items
are added while parsing various grammars into the AGM. And some
of them are unnecessary.
*/
if(debug!=null) debug.println("removing temporary class items");
TemporaryClassItemRemover.remove( grammar );
/*
perform field annotation. this will normalize
C-C/C-P/C-I relation and make up for missing FieldItems.
*/
if(debug!=null) debug.println("adding field items");
FieldItemAnnotation.annotate( grammar );
/*
finally perform overall normalization. This will ensure that
JavaItems are used correctly and compute various field values for
JavaItems.
*/
if(debug!=null) debug.println("normalizing relations");
RelationNormalizer.normalize( reader, grammar );
/*
removes ClassItems which corresponds to the definition of super-class.
this is necessary to produce marshallers correctly.
TODO: maybe this shouldn't be included here.
*/
if(debug!=null) debug.println("removing superClass body definition");
SuperClassBodyRemover.remove( grammar );
return grammar.topLevel;
}
}
msv-2009.1/tahiti/src/com/sun/tahiti/reader/annotator/TemporaryClassItemRemover.java 0000644 0001750 0001750 00000020155 07337343356 031017 0 ustar giovanni giovanni /*
* @(#)$Id: TemporaryClassItemRemover.java 1087 2001-08-18 01:37:50Z Bear $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.tahiti.reader.annotator;
import com.sun.msv.grammar.*;
import com.sun.msv.grammar.trex.ElementPattern;
import com.sun.msv.grammar.util.ExpressionWalker;
import com.sun.tahiti.grammar.*;
import com.sun.tahiti.grammar.util.Multiplicity;
import com.sun.tahiti.grammar.util.MultiplicityCounter;
import java.util.Set;
import java.util.Iterator;
/**
* removes temporarily added ClassItems (those ClassItems whose isTemporary field
* is true) if they are unnecessary.
*
*
* The current implementation employs the following criteria to find "unnecessary"
* class items.
*
*
*
Any ClassItem that are referenced from InterfaceItem or SuperClassItem
* cannot be removed. InterfaceItem requires its children to be a ClassItem,
* so does SuperClassItem. Thus we cannot remove them.
*
*
Any ClassItem that has more than one child ClassItem/InterfaceItem/
* PrimitiveItem cannot be removed.
* Those items are considered too complex to be removed.
*
*
Any ClassItem that can be reached from more than one ClassItem (or the top
* level expression) cannot be removed. Counting a reference from the top
* level expression is important. Otherwise a ClassItem will be removed
* if it is the only one ClassItem in the entire grammar.
*
*
* @author
* Kohsuke KAWAGUCHI
*/
class TemporaryClassItemRemover {
/** debug logger. */
private static java.io.PrintStream debug = System.out;
public static void remove( AnnotatedGrammar grammar ) {
// run the first pass and determine which class items can be removed.
Pass1 p1 = new Pass1();
grammar.topLevel.visit(p1);
Set cs = new java.util.HashSet(grammar.classes.values());
cs.removeAll( p1.notRemovableClasses );
// remove non-temporary classes from the set
// because they cannot be removed.
Iterator itr = cs.iterator();
while( itr.hasNext() )
if( !((ClassItem)itr.next()).isTemporary )
itr.remove();
if(debug!=null) {
itr = cs.iterator();
while( itr.hasNext() ) {
ClassItem ci = (ClassItem)itr.next();
debug.println( " "+ci.getTypeName()+" will be removed" );
}
}
// run the second pass and remove unnecessary class items.
grammar.topLevel = grammar.topLevel.visit(
new Pass2( grammar.getPool(), cs ) );
grammar.removeClassItems(cs);
}
/**
* computes exact ClassItems to be removed.
*/
private static class Pass1 extends ExpressionWalker implements JavaItemVisitor {
/** this set stores all examined ClassItems. */
private final Set checkedClasses = new java.util.HashSet();
/** this set stores ClassItems that are determined not to be removed. */
final Set notRemovableClasses = new java.util.HashSet();
/** this set stores all the children of the current ClassItem. */
private Set childItems = new java.util.HashSet();
private JavaItem parentItem;
public void onOther( OtherExp exp ) {
if(!(exp instanceof JavaItem )) {
// we don't know what this OtherExp is.
super.onOther(exp);
return;
}
((JavaItem)exp).visitJI(this);
}
public Object onIgnore( IgnoreItem item ) {
// since IgnoreItem is completely ignored, don't perform recursion.
return null;
}
public Object onField( FieldItem item ) {
// we are not interested in FieldItems now.
// just perform recursion.
super.onOther(item);
return null;
}
public Object onSuper( SuperClassItem item ) { updateAndVisit(item); return null; }
public Object onInterface( InterfaceItem item ) { updateAndVisit(item); return null; }
private void updateAndVisit( JavaItem item ) {
childItems.add(item);
// update the parentItem field, and check the body.
JavaItem old = parentItem;
parentItem=item;
super.onOther(item);
parentItem=old;
}
public Object onPrimitive( PrimitiveItem item ) {
// we don't need to check the body of a PrimitiveItem.
// just store it and return.
childItems.add(item);
return null;
}
public Object onClass( ClassItem item ) {
childItems.add(item); // this has to be done before the checkedClasses field is examined.
if((parentItem instanceof SuperClassItem)
|| (parentItem instanceof InterfaceItem)) {
// if a ClassItem is referenced from SuperClassItem or InterfaceItem,
// then it can't be removed.
if(notRemovableClasses.add(item))
if( debug!=null )
debug.println(item.getTypeName()+" : referenced by a superClass/interfaceItem");
}
if(!checkedClasses.add(item)) {
// if this ClassItem is already checked don't check it again.
// This also means that this ClassItem is referenced more than once.
// so this ClassItem cannot be removed.
if(notRemovableClasses.add(item))
if( debug!=null )
debug.println(item.getTypeName()+" : referenced more than once");
return null;
}
// prepare a fresh set to collect child JavaItems.
Set oldChildItems = childItems;
childItems = new java.util.HashSet();
JavaItem oldParent = parentItem;
parentItem = item;
// visit the children and see what are children of this ClassItem.
super.onOther(item);
if( childItems.size()==0 ) {
// if there is no child item, then probably
// the existance of this element is significant.
// so keep it.
if(notRemovableClasses.add(item))
if( debug!=null )
debug.println(item.getTypeName()+" : this class has no child item");
} else
if( childItems.size()>1 ) {
// if a ClassItem has more than one child items,
// then it cannot be removed.
if(notRemovableClasses.add(item))
if( debug!=null )
debug.println(item.getTypeName()+" : this class has multiple fields");
// } else {
// // if its sole child is not a primitive item, then it cannot
// // be removed either.
// if(!(childItems.iterator().next() instanceof PrimitiveItem ))
// notRemovableClasses.add(item);
}
childItems = oldChildItems;
parentItem = oldParent;
return null;
}
};
/**
* removes specified ClassItems.
*
* In this implementation, we don't propagate any information from the ancestor nodes
* to child nodes. Therefore it is safe to rewrite the body of ReferenceExp (and
* the content model field of ElementExps).
*/
private static class Pass2 extends ExpressionCloner {
Pass2( ExpressionPool pool, Set targets ) {
super(pool);
this.targets = targets;
}
/** ClassItems contained in this set will be removed by this procedure. */
private final Set targets;
// assertions. these method may never be called.
public Expression onNullSet() { throw new Error(); }
public Expression onConcur( ConcurExp exp ) { throw new Error(); }
// attribute/element.
public Expression onAttribute( AttributeExp exp ) {
Expression body = exp.exp.visit(this);
if( body==exp.exp ) return exp;
else return pool.createAttribute( exp.nameClass, body );
}
private final Set visitedExps = new java.util.HashSet();
public Expression onElement( ElementExp exp ) {
if( !visitedExps.add(exp) )
// this exp is already processed. this check will prevent infinite recursion.
return exp;
exp.contentModel = exp.contentModel.visit(this);
return exp;
}
public Expression onRef( ReferenceExp exp ) {
if( !visitedExps.add(exp) )
// this exp is already processed. this check will prevent infinite recursion.
return exp;
// update the definition and return self.
exp.exp = exp.exp.visit(this);
return exp;
}
public Expression onOther( OtherExp exp ) {
if( targets.contains(exp) ) {
if(debug!=null)
debug.println( " "+((ClassItem)exp).getTypeName()+": found and removed");
// this temporary class item is unnecessary. remove it.
// but don't forget to recurse its descendants.
return exp.exp.visit(this);
}
// update the definition and return self.
exp.exp = exp.exp.visit(this);
return exp;
}
};
}
msv-2009.1/tahiti/src/com/sun/tahiti/reader/annotator/FieldItemAnnotation.java 0000644 0001750 0001750 00000027026 07337343356 027571 0 ustar giovanni giovanni /*
* @(#)$Id: FieldItemAnnotation.java 1087 2001-08-18 01:37:50Z Bear $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.tahiti.reader.annotator;
import com.sun.msv.datatype.xsd.StringType;
import com.sun.msv.grammar.*;
import com.sun.msv.grammar.util.ExpressionWalker;
import com.sun.msv.grammar.util.ExpressionPrinter;
import com.sun.msv.grammar.trex.ElementPattern;
import com.sun.msv.grammar.xmlschema.SimpleTypeExp;
import com.sun.tahiti.grammar.*;
import com.sun.tahiti.grammar.util.Multiplicity;
import com.sun.tahiti.grammar.util.MultiplicityCounter;
import com.sun.tahiti.reader.NameUtil;
import java.util.Set;
import java.util.Map;
import java.util.Stack;
import java.util.Iterator;
/**
* adds missing FieldItems to the grammar.
*
* This algorithm expands C-C, C-I, and C-P relationships to
* C-F/F-C, C-F/F-I, and C-F/F-P relationships.
*
* @author
* Kohsuke KAWAGUCHI
*/
class FieldItemAnnotation
{
private static java.io.PrintStream debug = System.out;
public static void annotate( AnnotatedGrammar g ) {
FieldItemAnnotation ann = new FieldItemAnnotation();
// process all class items.
ClassItem[] classes = g.getClasses();
for( int i=0; i
When processing X->Z, we want to add extra FieldItem.
When processing Y->Z, we don't want that.
*/
Expression body = visitXMLItemContent(exp);
if(body==exp.contentModel) return exp;
else return new ElementPattern( exp.getNameClass(), body );
}
private Expression visitXMLItemContent( NameClassAndExpression exp ) {
// if this element or attribute has a simple name, then
// push it to the name stack.
String name=null;
NameClass nc = exp.getNameClass();
if( nc instanceof SimpleNameClass )
name = ((SimpleNameClass)nc).localName;
// if this is the direct child of the owner, do not push it to
// the name stack.
/*
Consider the following case. Typically, a ClassItem is created on .
In this case, ClassItem's exp field is an ElementExp.
....
In cases like this, it's silly to use "foo" as the name of children.
So don't push it to the name stack.
*/
if( exp==owner.exp )
name = null;
if(name!=null) names.push(name);
Expression body = exp.getContentModel().visit(this);
if(name!=null) names.pop();
return body;
}
/**
*
* For other live but not complex branches, if a branch doesn't contain
* FieldItems, then it is wrapped by a FieldItem. Since FieldItem cannot be
* wrapped by a FieldItem, we cannot wrap a branch by a FieldItem if
* it contains FieldItem. This case happens only when a user explicitly
* annotate a part of the grammar like this:
*
*
*
* In this case, we recursively process that branch (since that branch may
* contains other bare ClassItems.)
*
*
* All
*/
public Expression onChoice( ChoiceExp exp ) {
// check whether there is only one meaningul branch, or more than one of them.
Expression[] b = exp.getChildren();
boolean[] fieldlessBranch = new boolean[b.length];
int numLiveBranch = 0;
boolean bBranchWithField = false;
final boolean[] bBranchWithPrimitive = new boolean[1];
if(debug!=null) {
debug.println( "Processing Choice: " + ExpressionPrinter.printContentModel(exp) );
debug.println("checking each branch");
}
for( int i=0; i.
// visit all unvisited branch
for( int i=0; i=0 ) idx--;
idx++;
if(idx==name.length()) // the name doesn't have any number in its suffix.
names.push( name+"1" );
else // increment the number
names.push( name.substring(0,idx)+(Integer.parseInt(name.substring(idx))+1) );
return NameUtil.xmlNameToJavaName("field",name);
}
}
// /**
// * generates a field name suitable to hold a reference for the specified class.
// */
// private static String typeNameToFieldName( String bareName ) {
// return Character.toLowerCase(bareName.charAt(0))+bareName.substring(1);
// }
private static void assert( boolean b ) {
if(!b) throw new Error();
}
}
msv-2009.1/tahiti/src/com/sun/tahiti/reader/annotator/PrimitiveTypeAnnotator.java 0000644 0001750 0001750 00000004765 07365333167 030401 0 ustar giovanni giovanni package com.sun.tahiti.reader.annotator;
import com.sun.msv.grammar.*;
import com.sun.msv.datatype.DatabindableDatatype;
import com.sun.msv.datatype.xsd.StringType;
import com.sun.msv.util.StringPair;
import com.sun.tahiti.grammar.PrimitiveItem;
import java.util.Set;
import java.util.Map;
import org.relaxng.datatype.Datatype;
/**
* add PrimitiveItems to an AGM.
*
*
*
* replace Expression.anyString by <data type="string"/>
*
*
* wrap TypedStringExp by PrimitiveItem.
*
*
*
* @author
* Kohsuke KAWAGUCHI
*/
class PrimitiveTypeAnnotator extends ExpressionCloner {
PrimitiveTypeAnnotator( ExpressionPool pool ) {
super(pool);
}
/**
* processed Expressions. used to prevent infinite recursion.
*/
private final Set visitedExps = new java.util.HashSet();
/**
* a map from TypedStringExp to the PrimitiveItem which wraps it.
* used to unify PrimitiveItems.
*/
private final Map primitiveItems = new java.util.HashMap();
public Expression onRef( ReferenceExp exp ) {
if( visitedExps.add(exp) )
exp.exp = exp.exp.visit(this);
return exp;
}
public Expression onOther( OtherExp exp ) {
if( visitedExps.add(exp) )
exp.exp = exp.exp.visit(this);
return exp;
}
public Expression onElement( ElementExp exp ) {
if( visitedExps.add(exp) )
exp.contentModel = exp.contentModel.visit(this);
return exp;
}
public Expression onAttribute( AttributeExp exp ) {
if( visitedExps.contains(exp) ) return exp;
Expression e = pool.createAttribute( exp.nameClass, exp.exp.visit(this) );
visitedExps.add(e);
return e;
}
public Expression onAnyString() {
return new PrimitiveItem( StringType.theInstance,
pool.createData(StringType.theInstance) );
}
public Expression onValue( ValueExp exp ) { return onDataOrValue(exp); }
public Expression onData( DataExp exp ) { return onDataOrValue(exp); }
private Expression onDataOrValue( DataOrValueExp exp ) {
if( primitiveItems.containsKey(exp) )
// if this exp is already wrapped, use it instead of creating another one.
// this will reduce the size of the LL grammar for data-binding.
return (Expression)primitiveItems.get(exp);
else {
// if this is the first time, wrap it and memorize it.
Datatype dt = exp.getType();
PrimitiveItem p = new PrimitiveItem(
(dt instanceof DatabindableDatatype)?(DatabindableDatatype)dt:null,
(Expression)exp);
primitiveItems.put( exp, p );
return p;
}
}
}
msv-2009.1/tahiti/src/com/sun/tahiti/reader/annotator/RelationNormalizer.java 0000644 0001750 0001750 00000046273 07365333167 027521 0 ustar giovanni giovanni /*
* @(#)$Id: RelationNormalizer.java 1256 2001-10-23 18:27:03Z Bear $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.tahiti.reader.annotator;
import com.sun.msv.grammar.*;
import com.sun.msv.grammar.util.ExpressionWalker;
import com.sun.msv.grammar.trex.ElementPattern;
import com.sun.msv.reader.GrammarReader;
import com.sun.tahiti.grammar.*;
import com.sun.tahiti.grammar.util.Multiplicity;
import com.sun.tahiti.grammar.util.MultiplicityCounter;
import com.sun.tahiti.reader.TypeUtil;
import java.util.Set;
import org.xml.sax.Locator;
/**
* Normalizes the relationships between JavaItems.
*
*
1st pass
*
*
* Its first job is to check that prohibited relationships are not used.
* For example, super-super relationship is prohibited. See the design document
* for the complete list of the prohibited relationships.
*
*
* Its second job is to find the actual ClassItem for every SuperClassItem.
* There has to be one and only one ClassItem for each SuperClassItem,
* and its multiplicity must be '1'.
*
*
* Its third job is to make sure that a ClassItem has at most one SuperClassItem,
* and its multiplicity must be '1' or '?'.
*
*
* Its fourth job is to create a FieldUse object for each class-field relationship and
* connects a class and its fields. It is possible and allowed for one ClassItem object
* to have multiple FieldItem objects that share the same field name.
*
*
* Its fifth job is to process "interface-class" relationship. Whenever this is
* relationship is found, the fact that this class
* implements that interface is recorded.
* Its multiplicity must be (1,1). (It can be relaxed to allow (0,1))
*
*
*
* It also strips any tahiti declarations found under an IgnoreItem.
* For the unmarshaller to work correctly, IgnoreItem cannot have any tahiti
* items.
*
*
*
2nd pass
*
* In the 2nd pass, our first job is to compute the total multiplicity of each field.
* One ClassItem can have multiple FieldItem with the same name, and one FieldItem
* can have multiple TypeItem as its children.
*
*
* In the 1st pass, we've computed the multiplicity for every FieldItem. So before
* the 2nd pass, we are in the following situation:
*
*
* We'd like to know the "total" multiplicity of the field "abc". In this case,
* it will be (2,unbounded).
*
*
* Its next job is to compute the type of the field. Field values may have
* different types, and we need to compute the common base type.
*
* @author
* Kohsuke KAWAGUCHI
*/
class RelationNormalizer {
private RelationNormalizer( GrammarReader reader ) {
this.reader = reader;
}
private final GrammarReader reader;
/**
* performs the normalization.
*
* @param reader
* GrammarReader object which was responsible to parse the grammar.
* This object is used to report errors and obtain the source location
* for error messages.
* @param exp
* The top-level expression of the parsed grammar.
*
* @return
* The top-level expression of the normalized grammar.
*/
public static void normalize( GrammarReader reader, AnnotatedGrammar grammar ) {
RelationNormalizer n = new RelationNormalizer(reader);
ClassItem[] classItems = grammar.getClasses();
Pass1 pass1 = n.new Pass1();
grammar.topLevel = grammar.topLevel.visit(pass1);
for( int i=0; i
When processing X->Z, we want to add extra FieldItem.
When processing Y->Z, we don't want that.
*/
Expression body = exp.contentModel.visit(this);
if(body==exp.contentModel) return exp;
return new ElementPattern( exp.getNameClass(), body );
}
public Expression onMixed( MixedExp exp ) {
// doesn't affect the multiplicity.
return reader.pool.createMixed(exp.exp.visit(this));
}
public Expression onList( ListExp exp ) {
// itself doesn't affect the multiplicity.
return reader.pool.createList(exp.exp.visit(this));
}
public Expression onConcur( ConcurExp exp ) {
// possibly, it can be served by ignoring all but one branch.
throw new Error("concur is not supported");
}
public Expression onChoice( ChoiceExp exp ) {
Expression lhs = exp.exp1.visit(this);
Multiplicity lhc = multiplicity;
Expression rhs = exp.exp2.visit(this);
Multiplicity rhc = multiplicity;
multiplicity = Multiplicity.choice(lhc,rhc);
return reader.pool.createChoice( lhs, rhs );
}
public Expression onSequence( SequenceExp exp ) {
Expression lhs = exp.exp1.visit(this);
Multiplicity lhc = multiplicity;
Expression rhs = exp.exp2.visit(this);
Multiplicity rhc = multiplicity;
multiplicity = Multiplicity.group(lhc,rhc);
return reader.pool.createSequence( lhs, rhs );
}
public Expression onInterleave( InterleaveExp exp ) {
Expression lhs = exp.exp1.visit(this);
Multiplicity lhc = multiplicity;
Expression rhs = exp.exp2.visit(this);
Multiplicity rhc = multiplicity;
multiplicity = Multiplicity.group(lhc,rhc);
return reader.pool.createInterleave( lhs, rhs );
}
public Expression onOneOrMore( OneOrMoreExp exp ) {
Expression p = reader.pool.createOneOrMore( exp.exp.visit(this) );
multiplicity = Multiplicity.oneOrMore(multiplicity);
return p;
}
// terminal items. starts with multiplicity (0,0)
public Expression onEpsilon() {
multiplicity = Multiplicity.zero;
return Expression.epsilon;
}
public Expression onNullSet() {
// nullSet should have been completely removed.
throw new Error();
}
public Expression onAnyString() {
// anyString should have been completely removed.
throw new Error();
}
public Expression onData( DataExp exp ) {
multiplicity = Multiplicity.zero;
return exp;
}
public Expression onValue( ValueExp exp ) {
multiplicity = Multiplicity.zero;
return exp;
}
public Expression onRef( ReferenceExp exp ) {
return exp.exp.visit(this);
}
// Java items
//=======================================
public Expression onOther( OtherExp exp ) {
// if it's not a java item,
// simply recurse its contents.
// note that we can't update exp.exp by the modified expressions.
if(!(exp instanceof JavaItem))
return exp.exp.visit(this);
// skip any JavaItem if it is in an ignored item.
// this will effectively clone the entire descendants of the
// IgnoreItem.
if( isIgnore(parentItem) )
return exp.exp.visit(this);
JavaItem old = parentItem;
if( exp instanceof JavaItem ) {
// this is a java item.
// check if this relation is allowed.
// several relationships are prohibited (like S-S).
sanityCheck( parentItem, (JavaItem)exp );
if( isSuperClass(parentItem) && isClass(exp) )
setSuperClassBody( (SuperClassItem)parentItem, (ClassItem)exp );
if( isInterface(parentItem) && isType(exp) )
setImplementedInterface( (TypeItem)exp, (InterfaceItem)parentItem );
if( isClass(parentItem) && isSuperClass(exp) )
// this is a super class to the parent class item.
setSuperClassForClass( (ClassItem)parentItem, (SuperClassItem)exp );
if( isClass(parentItem) && isField(exp) ) {
// this is a field to the parent class item.
FieldItem fi = (FieldItem)exp;
((ClassItem)parentItem).getFieldUse(fi.name).items.add(fi);
}
if( isField(parentItem) && (exp instanceof Type) )
((FieldItem)parentItem).types.add(exp);
if( !visitedClasses.add(exp) ) {
multiplicity = getJavaItemMultiplicity(exp);
// this one is a java item and already processed.
// so there is no need to traverse it again.
// to prevent infinite recursion, return immediately.
return exp;
}
// then change the parent item to this object.
parentItem = (JavaItem)exp;
}
// visit children
exp.exp = exp.exp.visit(this);
parentItem = old;
// make sure that this class item is defined properly.
// this part of the code is executed only once per each JavaItem.
if( isSuperClass(exp) ) {
// super class item must have its definition.
SuperClassItem sci = (SuperClassItem)exp;
if( sci.definition==null ) {
reader.reportError(
new Locator[]{reader.getDeclaredLocationOf(exp)},
ERR_MISSING_SUPERCLASS_BODY,
null );
}
else {
// if we couldn't find the definition, do not report this error.
// S-C multiplicity must be (1,1)
if( !multiplicity.isUnique() ) {
reader.reportError(
new Locator[]{
reader.getDeclaredLocationOf(exp),
reader.getDeclaredLocationOf(sci.definition)},
ERR_BAD_SUPERCLASS_BODY_MULTIPLICITY,
new Object[]{sci.definition.name} );
}
}
}
if( isField(exp) ) {
// store the multiplicity of this field.
((FieldItem)exp).multiplicity = multiplicity;
}
if( isInterface(exp) ) {
// I-I/I-C multiplicity must be (1,1)
InterfaceItem ii = (InterfaceItem)exp;
if( !multiplicity.isAtMostOnce() ) {
// DBG
System.out.println( com.sun.msv.grammar.util.ExpressionPrinter.printContentModel(exp.exp) );
reader.reportError(
new Locator[]{reader.getDeclaredLocationOf(ii)},
ERR_BAD_INTERFACE_CLASS_MULTIPLICITY,
new Object[]{ ii.name } );
}
// InterfaceItem returns the multiplicity of its children.
// so don't touch the multiplicity field
return exp;
}
multiplicity = getJavaItemMultiplicity(exp);
return exp;
}
private Multiplicity getJavaItemMultiplicity( OtherExp item ) {
if( item instanceof IgnoreItem ) return Multiplicity.zero;
else return Multiplicity.one;
}
/**
* performs sanity check for the use of roles.
*/
private void sanityCheck( JavaItem parent, JavaItem child ) {
if( isSuperClass(parent) && !isClass(child) ) {
// super-field, super-super, super-interface.
reader.reportError(
new Locator[]{
reader.getDeclaredLocationOf(parent),
reader.getDeclaredLocationOf(child)},
ERR_BAD_SUPERCLASS_USE, null );
return;
}
if( isPrimitive(parent) )
// primitive-*.
// since PrimitiveItems are not specified by the user,
// it must be an internal error.
throw new Error("internal error: use of primitive-* relation.");
if(( isField(parent) && ( isSuperClass(child) || isField(child)) )
|| ( isInterface(parent) && ( isSuperClass(child) || isField(child) || isPrimitive(child) ) ) ) {
// I-S, I-F, F-S, F-F, F-P relationship.
// TODO: diagnose better
reader.reportError(
new Locator[]{
reader.getDeclaredLocationOf(parent),
reader.getDeclaredLocationOf(child)},
ERR_BAD_ITEM_USE, null );
return;
}
if( isClass(parent) && (child instanceof Type) ) {
// class-class, class-interface, or class-primitive relation.
// FieldItemAnnotator should run before this process
// to prevent such situations from happening in the normalizer.
throw new Error("internal error. C-C/C-I/C-P relation "
+ ((ClassItem)parent).getTypeName()+" "+
child.toString()+
" "+ com.sun.msv.grammar.util.ExpressionPrinter.printContentModel(parent) );
}
}
/**
* this method is called when class-super relationship is found, and after
* all the descendants of "super" is processed.
*/
protected void setSuperClassForClass( ClassItem p, SuperClassItem c ) {
// C-S multiplicity check has to be done in the 2nd pass.
/*
if( multiplicity!='1' && multiplicity!='?' ) {
reader.reportError(
new Locator[]{
reader.getDeclaredLocationOf(p),
reader.getDeclaredLocationOf(c)},
ERR_BAD_SUPERCLASS_CARDINALITY,
new Object[]{p.name} );
return;
}
*/
if( p.superClass!=null ) {
// this parent item already has a super class.
reader.reportError(
new Locator[]{
reader.getDeclaredLocationOf(p), // parent class item
reader.getDeclaredLocationOf(p.superClass), // previous super class definition.
reader.getDeclaredLocationOf(c)}, // newly found super class definition.
ERR_MULTIPLE_INHERITANCE,
new Object[]{p.name} );
return;
}
p.superClass = c;
}
/**
* this method is called when super-class relationship is found, and before
* the descendants of "class" is processed.
*/
protected void setSuperClassBody( SuperClassItem parent, ClassItem child ) {
// set the definition field of SuperClassItem.
if( parent.definition!=null ) {
/* two definitions are found. This happens for patterns like
....
....
*/
reader.reportError(
new Locator[]{
reader.getDeclaredLocationOf(parent),
reader.getDeclaredLocationOf(child),
reader.getDeclaredLocationOf(parent.definition)
},
ERR_MULTIPLE_SUPERCLASS_BODY, null );
// recover by ignoring this definition.
return;
}
parent.definition = child;
}
/**
* this method is called when interface-class/interface-interface relationship
* is found, and before the descendants of "class" is processed.
*/
protected void setImplementedInterface( TypeItem c, InterfaceItem i ) {
c.interfaces.add(i);
}
/**
* this set contains all visited ClassItem objects.
* used to prevent infinite recursion.
*/
private final Set visitedClasses = new java.util.HashSet();
/**
* this field holds the parent item object.
*/
private JavaItem parentItem = null;
/**
* multiplicity from the current parent (either '1', '?', '+', or '*').
*
* '1' means "exactly once", '?' means "zero or one", '+' means
* "one or more", and '*' means "zero or more".
* This value represents how many times this expression can be matched
* for one parent item.
*
*
* For example, consider the following expression:
*
* <group> <-- parent
* <oneOrMore>
* <choice>
* <element/> <-- child
* <element/>
* </choice>
* </oneOrMore>
* </group>
*
*
* for one parent item, child item can appear '*' times.
*/
private Multiplicity multiplicity = null;
}
/**
* computes the total multiplicity of a FieldUse.
*/
private class Pass2 extends MultiplicityCounter {
Pass2( FieldUse fieldUse ) {
this.fieldUse = fieldUse;
}
private final FieldUse fieldUse;
protected Multiplicity isChild( Expression exp ) {
// if this is a FieldItem and it counts, then
// return its multiplicity.
if( fieldUse.items.contains(exp) ) {
if( ((FieldItem)exp).multiplicity==null)
throw new Error("internal error");
return ((FieldItem)exp).multiplicity;
}
// if it is a JavaItem, return (0,0).
if( exp instanceof JavaItem )
return Multiplicity.zero;
// otherwise recurse to the children
return null;
}
}
// type check utility methods.
//=================================================
private static boolean isClass( Object exp ) {
return exp instanceof ClassItem;
}
private static boolean isSuperClass( Object exp ) {
return exp instanceof SuperClassItem;
}
private static boolean isInterface( Object exp ) {
return exp instanceof InterfaceItem;
}
private static boolean isField( Object exp ) {
return exp instanceof FieldItem;
}
private static boolean isType( Object exp ) {
return exp instanceof TypeItem;
}
private static boolean isPrimitive( Object exp ) {
return exp instanceof PrimitiveItem;
}
private static boolean isIgnore( Object exp ) {
return exp instanceof IgnoreItem;
}
// Normalizer error messages.
public static final String ERR_BAD_SUPERCLASS_USE = // arg:0
"Normalizer.BadSuperClassUse";
public static final String ERR_BAD_ITEM_USE = // arg:0
"Normalizer.BadItemUse";
public static final String ERR_MULTIPLE_SUPERCLASS_BODY = // arg:0
"Normalizer.MultipleSuperClassBody"; // more than one class items match a superClass item.
public static final String ERR_MULTIPLE_INHERITANCE = // arg:1
"Normalizer.MultipleInheritance"; // more than one super class items are found for a class item "{0}".
public static final String ERR_MISSING_SUPERCLASS_BODY = // arg:1
"Normalizer.MissingSuperClassBody"; // super class item "{0}" doesn't have a child class item.
public static final String ERR_BAD_SUPERCLASS_MULTIPLICITY = // arg:1
"Normalizer.BadSuperClassMultiplicity"; // class item "{0}" can possibly match its super class several times.
public static final String ERR_BAD_SUPERCLASS_BODY_MULTIPLICITY = // arg:1
"Normalizer.BadSuperClassBodyMultiplicity"; // a super class item can reach this class item "{0}" more than once, or maybe zero.
public static final String ERR_BAD_INTERFACE_CLASS_MULTIPLICITY = // arg:1
"Normalizer.BadInterfaceToClassMultiplicity"; // the interface item "{1}" may have repeated children or is epsilon-reducible.
}
msv-2009.1/tahiti/src/com/sun/tahiti/reader/annotator/ChoiceAnnotator.java 0000644 0001750 0001750 00000024671 07365333167 026757 0 ustar giovanni giovanni /*
* @(#)$Id: ChoiceAnnotator.java 1256 2001-10-23 18:27:03Z Bear $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.tahiti.reader.annotator;
import com.sun.msv.datatype.xsd.StringType;
import com.sun.msv.grammar.*;
import com.sun.msv.grammar.util.ExpressionWalker;
import com.sun.msv.grammar.util.ExpressionPrinter;
import com.sun.msv.grammar.trex.ElementPattern;
import com.sun.msv.grammar.xmlschema.SimpleTypeExp;
import com.sun.tahiti.grammar.*;
import com.sun.tahiti.grammar.util.Multiplicity;
import com.sun.tahiti.grammar.util.MultiplicityCounter;
import com.sun.tahiti.reader.NameUtil;
import java.util.Set;
import java.util.Map;
import java.util.Stack;
import java.util.Iterator;
/**
* annotates <choice> with ClassItem/InterfaceItem
* so that it can be handled easily.
*
* @author
* Kohsuke KAWAGUCHI
*/
class ChoiceAnnotator
{
private static java.io.PrintStream debug = null;
public static void annotate( AnnotatedGrammar g ) {
ChoiceAnnotator ann = new ChoiceAnnotator(g);
// process all class items.
ClassItem[] classes = g.getClasses();
for( int i=0; i
When processing X->Z, we want to add extra FieldItem.
When processing Y->Z, we don't want that.
*/
Expression body = exp.contentModel.visit(this);
if(body==exp.contentModel) return exp;
else return new ElementPattern( exp.getNameClass(), body );
}
/**
* annotate ChoiceExp with FieldItem.
*
*
* children of a ChoiceExp is called "branches". In this method,
* branches of the entire choice group is considered.
*
*
* We consider a branch is "alive" if there is some JavaItem in that branch.
* For example, <empty> is not a live branch. IgnoreItem is another
* example of non-live branch.
*
*
* If only one branch out of the entire branches is alive, then this choice
* is not treated at all, and the live branch is recursively processed.
* This handles <optional> p </optional>.
*
*
* Otherwise, the following algorithm is applied:
*
*
* A branch is said to be "complex", if the multiplicity of child JavaItem is
* more than one. For example,
*
*
* is a complex branch. If a branch is complex, then it is wrapped by a
* ClassItem. Wrapping by a ClassItem makes its
* multiplicity (1,1). This ensures that every branch has the multiplicity
* of at-most-one.
*/
public Expression onChoice( ChoiceExp exp ) {
// check whether there is only one meaningul branch, or more than one of them.
Expression[] b = exp.getChildren();
boolean[] complexBranch = new boolean[b.length];
boolean[] fieldlessBranch = new boolean[b.length];
int numLiveBranch = 0;
boolean bBranchWithField = false;
final boolean[] bBranchWithPrimitive = new boolean[1];
if(debug!=null) {
debug.println( "Processing Choice: " + ExpressionPrinter.printContentModel(exp) );
debug.println("checking each branch");
}
for( int i=0; i.
// visit all unvisited branch
for( int i=0; i as
exp.exp
*/
Expression expanded = pool.createInterleave(
pool.createZeroOrMore(
new PrimitiveItem( StringType.theInstance,
pool.createData(StringType.theInstance) )),
exp.exp );
try {
// see if "exp" contains FieldItem.
exp.exp.visit( new ExpressionWalker(){
public void onOther( OtherExp exp ) {
if(exp instanceof FieldItem) throw eureka;
if(exp instanceof JavaItem) return;
super.onOther(exp);
}
});
} catch(RuntimeException e) {
// if there is a field item in it,
// then visit "expanded".
// typically this will loose the order between characters and
// elements, but this seems to be a reasonable compromise.
assert(e==eureka);
return expanded.visit(this);
}
return expanded;
}
}
private static void assert( boolean b ) {
if(!b) throw new Error();
}
}
msv-2009.1/tahiti/src/com/sun/tahiti/reader/xmlschema/ 0000755 0001750 0001750 00000000000 11622453065 022765 5 ustar giovanni giovanni msv-2009.1/tahiti/src/com/sun/tahiti/reader/xmlschema/TAnyElementState.java 0000644 0001750 0001750 00000002637 07330362475 027033 0 ustar giovanni giovanni package com.sun.tahiti.reader.xmlschema;
import com.sun.msv.grammar.Expression;
import com.sun.msv.reader.State;
import com.sun.msv.reader.xmlschema.AnyElementState;
import com.sun.tahiti.grammar.FieldItem;
import com.sun.tahiti.grammar.IgnoreItem;
import com.sun.tahiti.reader.TahitiGrammarReader;
public class TAnyElementState extends AnyElementState {
protected Expression createExpression( String namespace, String process ) {
return wrap( process, this, "otherElements",
super.createExpression(namespace,process) );
}
static Expression wrap( String process, State owner, String defaultFieldName, Expression body ) {
if( process.equals("skip") ) {
// if the skip is specified, probably these elements are unnecessary.
// so ignore about them.
IgnoreItem ii = new IgnoreItem( body );
owner.reader.setDeclaredLocationOf(ii);
return ii;
}
if( process.equals("strict") || process.equals("lax") ) {
// place them into a special field.
// an "any" corresponds to the global element declarations.
// global element declarations are automatically wrapped by
// (temporary) class items.
String name = owner.getStartTag().getAttribute(
TahitiGrammarReader.TahitiNamespace,"name");
if(name==null) name=defaultFieldName;
FieldItem fi = new FieldItem(name, body);
owner.reader.setDeclaredLocationOf(fi);
return fi;
}
throw new Error(); // unknown processing mode.
}
}
msv-2009.1/tahiti/src/com/sun/tahiti/reader/xmlschema/TAnyAttributeState.java 0000644 0001750 0001750 00000001017 07326165503 027372 0 ustar giovanni giovanni package com.sun.tahiti.reader.xmlschema;
import com.sun.msv.grammar.Expression;
import com.sun.msv.reader.xmlschema.AnyAttributeState;
import com.sun.tahiti.grammar.FieldItem;
import com.sun.tahiti.grammar.IgnoreItem;
import com.sun.tahiti.reader.TahitiGrammarReader;
public class TAnyAttributeState extends AnyAttributeState {
protected Expression createExpression( String namespace, String process ) {
return TAnyElementState.wrap( process, this, "otherAttributes",
super.createExpression(namespace,process) );
}
}
msv-2009.1/tahiti/src/com/sun/tahiti/reader/xmlschema/TXMLSchemaReader.java 0000644 0001750 0001750 00000013662 07330362475 026675 0 ustar giovanni giovanni /*
* @(#)$Id: TXMLSchemaReader.java 970 2001-07-27 22:03:41Z Bear $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.tahiti.reader.xmlschema;
import com.sun.tahiti.grammar.AnnotatedGrammar;
import com.sun.tahiti.grammar.ClassItem;
import com.sun.tahiti.grammar.IgnoreItem;
import com.sun.tahiti.reader.TahitiGrammarReader;
import com.sun.tahiti.reader.NameUtil;
import com.sun.tahiti.reader.annotator.Annotator;
import com.sun.msv.reader.GrammarReaderController;
import com.sun.msv.reader.State;
import com.sun.msv.reader.xmlschema.XMLSchemaReader;
import com.sun.msv.grammar.ExpressionPool;
import com.sun.msv.grammar.xmlschema.ElementDeclExp;
import com.sun.msv.grammar.xmlschema.ComplexTypeExp;
import com.sun.msv.grammar.xmlschema.XMLSchemaSchema;
import com.sun.msv.util.StartTagInfo;
import org.xml.sax.InputSource;
import org.xml.sax.SAXException;
import org.xml.sax.Attributes;
import java.util.Map;
import java.util.Set;
import java.util.Stack;
import java.util.ResourceBundle;
import javax.xml.parsers.SAXParserFactory;
import java.text.MessageFormat;
public class TXMLSchemaReader extends XMLSchemaReader implements TahitiGrammarReader {
public TXMLSchemaReader(
GrammarReaderController controller,
SAXParserFactory parserFactory ) {
super( controller, parserFactory, new StateFactory(), new ExpressionPool() );
// ignore the body of ur-type.
complexUrType.exp = new IgnoreItem(complexUrType.exp);
// ignore the schema location attribute
xsiSchemaLocationExp.exp = new IgnoreItem( xsiSchemaLocationExp.exp );
}
protected final AnnotatedGrammar annGrammar = new AnnotatedGrammar( null, pool );
public AnnotatedGrammar getAnnotatedResult() {
return annGrammar;
}
/**
* gets the current XMLSchemaSchema object.
*/
protected XMLSchemaSchema getCurrentSchema() {
return super.currentSchema;
}
/**
* a map from ElementDeclExp to its ClassItem.
*/
private final Map elementToClass = new java.util.HashMap();
protected void addElementClass( ElementDeclExp exp, ClassItem cls ) {
elementToClass.put( exp, cls );
}
protected ClassItem getElementClass( ElementDeclExp exp ) {
return (ClassItem)elementToClass.get(exp);
}
/**
* computes the name of the generated Java item.
*
* @param owner
* State object which is currently in charge. The start tag of this
* State is used to find a name. First, the tahiti:name attribute is used.
* If not present, the name attribute is used.
* @param type
* For example, "interface" or "class". This parameter specifies the
* type of the Java item. This parameter is used to modify the naming
* convention. See {@link NameUtil#xmlNameToJavaName} for available values.
*
*/
protected String computeTypeName( State owner, String type ) {
String packageName = defaultPackageName;
if( packageName.length()!=0 ) packageName+=".";
// check the t:name attribute first.
String name = owner.getStartTag().getAttribute(TahitiGrammarReader.TahitiNamespace,"name");
if(name!=null) return packageName+name;
// use the name of the element.
name = owner.getStartTag().getAttribute("name");
if(name!=null) return packageName+NameUtil.xmlNameToJavaName(type,name);
// this must be an error.
return null;
}
public void wrapUp() {
// First, let the super class do its job.
super.wrapUp();
// if we already have an error, abort further processing.
if(hadError) return;
// if no package name is specified, place it to the root pacakge.
if(annGrammar.grammarName==null)
annGrammar.grammarName = "Grammar";
// add missing annotations and normalizes them.
annGrammar.topLevel = grammar.topLevel;
Annotator.annotate( annGrammar, this );
grammar.topLevel = annGrammar.topLevel;
}
// several State objects are replaced to annotated AGM with Tahiti items.
public static class StateFactory extends XMLSchemaReader.StateFactory {
protected State complexTypeDecl (State parent,StartTagInfo tag) { return new TComplexTypeDeclState(); }
protected State elementDecl (State parent,StartTagInfo tag) { return new TElementDeclState(); }
protected State any (State parent,StartTagInfo tag) { return new TAnyElementState(); }
protected State anyAttribute (State parent,StartTagInfo tag) { return new TAnyAttributeState(); }
// complexContent/extension
protected State complexExt (State parent,StartTagInfo tag, ComplexTypeExp decl) { return new TComplexContentBodyState(decl,true); }
}
/**
* propagatable 't:package' attribute that specifies the default package
* for unqualified java classes/interfaces.
*/
private final Stack packageNameStack = new Stack();
private String defaultPackageName="";
public void startElement( String a, String b, String c, Attributes d ) throws SAXException {
// handle "t:package" attribute here.
packageNameStack.push(defaultPackageName);
if( d.getIndex(TahitiNamespace,"package")!=-1 ) {
defaultPackageName = d.getValue(TahitiNamespace,"package");
// if this is the first time the package name is specified,
// then use it for the grammar's name.
if(annGrammar.grammarName==null)
annGrammar.grammarName = defaultPackageName+".Grammar";
}
super.startElement(a,b,c,d);
}
public void endElement( String a, String b, String c ) throws SAXException {
super.endElement(a,b,c);
defaultPackageName = (String)packageNameStack.pop();
}
protected String localizeMessage( String propertyName, Object[] args ) {
String format;
try {
format = ResourceBundle.getBundle(
"com.sun.tahiti.reader.xmlschema.Messages").getString(propertyName);
} catch( Exception e ) {
try {
format = ResourceBundle.getBundle(
"com.sun.tahiti.reader.Messages").getString(propertyName);
} catch( Exception ee ) {
return super.localizeMessage(propertyName,args);
}
}
return MessageFormat.format(format, args );
}
}
msv-2009.1/tahiti/src/com/sun/tahiti/reader/xmlschema/TElementDeclState.java 0000644 0001750 0001750 00000010437 07365333167 027154 0 ustar giovanni giovanni package com.sun.tahiti.reader.xmlschema;
import com.sun.msv.grammar.*;
import com.sun.msv.grammar.xmlschema.ElementDeclExp;
import com.sun.msv.reader.GrammarReader;
import com.sun.msv.reader.State;
import com.sun.msv.reader.xmlschema.ElementDeclState;
import com.sun.tahiti.grammar.ClassItem;
import com.sun.tahiti.grammar.InterfaceItem;
import com.sun.tahiti.reader.TahitiGrammarReader;
public class TElementDeclState extends ElementDeclState {
protected Expression annealExpression(Expression contentType) {
final Expression body = super.annealExpression(contentType);
final TXMLSchemaReader reader = (TXMLSchemaReader)this.reader;
if(!isGlobal())
// we assign ClassItem only when the element type is a global one.
return body;
if( "none".equals(startTag.getAttribute(TahitiGrammarReader.TahitiNamespace,"role")) )
// if "none" is specified, suppress a ClassItem.
// note that t:role could be possibly missing.
return body;
String name = startTag.getAttribute("name");
if(name==null)
// a global element decl must have a name. If not, it is an error.
return body; // abort
final ElementDeclExp decl = reader.getCurrentSchema().elementDecls.getOrCreate(name);
if( startTag.containsAttribute("substitutionGroup") ) {
// if this element decl has a substitution affiliation,
// back-patch the head and add InterfaceItem.
// since decl.substitutionAffiliation may be still not forged,
// we cannot add InterfaceItem now.
reader.addBackPatchJob( new GrammarReader.BackPatch(){
public State getOwnerState() {
return TElementDeclState.this;
}
public void patch() {
if( decl.substitutionAffiliation.exp instanceof InterfaceItem )
// someone has already added an InterfaceItem. abort.
return;
ClassItem head = reader.getElementClass(decl.substitutionAffiliation);
if(head==null)
// this substitution head doesn't have a ClassItem.
// there is something wrong. So abort now.
return;
// append "I" to the class name and use it.
String className="";
if( head.getPackageName()!=null )
className = head.getPackageName()+".";
className += "I"+head.getBareName();
InterfaceItem ii =
reader.annGrammar.createInterfaceItem( className,
decl.substitutionAffiliation.exp );
decl.substitutionAffiliation.exp = ii;
reader.setDeclaredLocationOf(ii);
}
});
}
final String className = reader.computeTypeName(this,"class");
if(className==null) return body; // abort
/* add a ClassItem in the element declaration.
decl.exp should be made from ChoiceExp, ElementDeclExps of
substitution groups, and ElementDeclExp.XSElementExp.
Or possibly nullSet (if there was an error or the element decl is abstract).
*/
decl.exp = decl.exp.visit( new ExpressionVisitorExpression(){
// do not touch those primitives.
public Expression onRef( ReferenceExp exp ) { return exp; }
public Expression onList( ListExp exp ) { return exp; }
public Expression onData( DataExp exp ) { return exp; }
public Expression onValue( ValueExp exp ) { return exp; }
public Expression onMixed( MixedExp exp ) { return exp; }
public Expression onEpsilon() { return Expression.epsilon; }
public Expression onAnyString() { return Expression.anyString; }
public Expression onNullSet() { return Expression.nullSet; }
public Expression onSequence( SequenceExp exp ) { return exp; }
public Expression onConcur( ConcurExp exp ) { return exp; }
public Expression onOther( OtherExp exp ) { return exp; }
public Expression onAttribute( AttributeExp exp ) { return exp; }
public Expression onOneOrMore( OneOrMoreExp exp ) { return exp; }
public Expression onInterleave( InterleaveExp exp ) { return exp; }
public Expression onChoice( ChoiceExp exp ) {
// recursively process choices.
return reader.pool.createChoice( exp.exp1.visit(this), exp.exp2.visit(this) );
}
public Expression onElement( ElementExp exp ) {
if( exp!=decl.body ) return exp;
// this is the element that we are looking for.
// wrap it by a ClassItem.
ClassItem item = reader.annGrammar.createClassItem( className, exp );
reader.setDeclaredLocationOf(item);
reader.addElementClass( decl, item );
return item;
}
});
return body;
}
}
msv-2009.1/tahiti/src/com/sun/tahiti/reader/xmlschema/TComplexTypeDeclState.java 0000644 0001750 0001750 00000001723 07335074714 030027 0 ustar giovanni giovanni package com.sun.tahiti.reader.xmlschema;
import com.sun.msv.grammar.Expression;
import com.sun.msv.reader.xmlschema.ComplexTypeDeclState;
import com.sun.tahiti.reader.TahitiGrammarReader;
public class TComplexTypeDeclState extends ComplexTypeDeclState {
protected Expression annealExpression(Expression contentType) {
final Expression body = super.annealExpression(contentType);
final TXMLSchemaReader reader = (TXMLSchemaReader)this.reader;
if( !isGlobal() )
// we assign ClassItem only when the complex type is a global one.
return body;
if( "none".equals(startTag.getAttribute(TahitiGrammarReader.TahitiNamespace,"role")) )
// if "none" is specified, suppress a ClassItem.
// note that t:role could be possibly missing.
return body;
// insert a ClassItem.
decl.body.exp = reader.annGrammar.createClassItem( reader.computeTypeName(this,"class"), decl.body.exp );
reader.setDeclaredLocationOf(decl.body.exp);
return body;
}
}
msv-2009.1/tahiti/src/com/sun/tahiti/reader/xmlschema/TComplexContentBodyState.java 0000644 0001750 0001750 00000001521 07335074714 030542 0 ustar giovanni giovanni package com.sun.tahiti.reader.xmlschema;
import com.sun.msv.reader.xmlschema.ComplexContentBodyState;
import com.sun.msv.grammar.Expression;
import com.sun.msv.grammar.xmlschema.ComplexTypeExp;
import com.sun.tahiti.grammar.SuperClassItem;
public class TComplexContentBodyState extends ComplexContentBodyState {
protected TComplexContentBodyState( ComplexTypeExp parentDecl, boolean extension ) {
super(parentDecl,extension);
}
/**
* combines the base type content model and this content model
*/
protected Expression combineToBaseType( ComplexTypeExp baseType, Expression addedExp ) {
if( extension ) {
SuperClassItem si = new SuperClassItem(baseType.body);
reader.setDeclaredLocationOf(si);
return reader.pool.createSequence( si, addedExp );
} else
// what shall we do if it's a restriciton.
return addedExp;
}
}
msv-2009.1/tahiti/src/com/sun/tahiti/reader/xmlschema/TGroupState.java 0000644 0001750 0001750 00000002052 07330362475 026055 0 ustar giovanni giovanni package com.sun.tahiti.reader.xmlschema;
import com.sun.msv.grammar.Expression;
import com.sun.msv.grammar.xmlschema.GroupDeclExp;
import com.sun.msv.reader.xmlschema.GroupState;
import com.sun.tahiti.grammar.ClassItem;
public class TGroupState extends GroupState {
protected Expression annealExpression(Expression contentType) {
final Expression body = super.annealExpression(contentType);
final TXMLSchemaReader reader = (TXMLSchemaReader)this.reader;
if(!isGlobal())
// if it's not a global one, then it is a reference to a model group.
// So do nothing.
return body;
if(!(body instanceof GroupDeclExp ))
// if this is a valid global model group definition,
// it should return GroupDeclExp.
return body;
// insert a temporary class item.
// maybe it shouldn't be temporary...
GroupDeclExp g = (GroupDeclExp)body;
ClassItem cls = reader.annGrammar.createClassItem(
reader.computeTypeName(this,"class"), g.exp );
cls.isTemporary = true;
reader.setDeclaredLocationOf(cls);
g.exp = cls;
return g;
}
}
msv-2009.1/tahiti/src/com/sun/tahiti/reader/Messages.properties 0000644 0001750 0001750 00000002241 07337072463 024677 0 ustar giovanni giovanni
#
# reader error
#
InvalidCollectionType = \
The value of the "t:collection" attribute must be either vector, list or set.
InvalidAccessModifier = \
The value of the "t:access" attribute must be either public, protected or private.
InvalidAccessor = \
The value of the "t:method" attribute must be either field, readonly or readwrite.
#
# normalizer error
#
Normalizer.BadSuperClassUse = \
"superClass" item can be referenced only from "class" items.
Normalizer.BadItemUse = \
this parent item is not allowed for this child item.
Normalizer.MultipleSuperClassBody = \
This "superClass" item has multiple children.
Normalizer.MultipleInheritance = \
more than one super class items are found for the class item "{0}".
Normalizer.MissingSuperClassBody = \
the super class item "{0}" doesn't have a child class item.
Normalizer.BadSuperClassMultiplicity = \
class item "{0}" can possibly match its super class several times.
Normalizer.BadSuperClassBodyMultiplicity = \
a super class item can reach its child class item "{0}" more than once, or maybe zero.
Normalizer.BadInterfaceToClassMultiplicity = \
the interface item "{0}" may match multiple children.
msv-2009.1/tahiti/src/com/sun/tahiti/reader/NameUtil.java 0000644 0001750 0001750 00000004441 07330362450 023366 0 ustar giovanni giovanni /*
* @(#)$Id: NameUtil.java 969 2001-07-27 22:03:20Z Bear $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.tahiti.reader;
/**
* Identifier-related utility methods.
*
* @author
* Kohsuke KAWAGUCHI
*/
public class NameUtil
{
/** convert a name to Java-compatible identifier name. */
public static String toIdentifier( String name ) {
return xmlNameToJavaName("field",name);
}
/**
* convert XML names (like element names) to the corresponding Java names.
*
* This method should perform conversion like ("abc"->"Abc").
*
* @param role
* the role of this expression. One of "field","interface", and "class".
*/
public static String xmlNameToJavaName( String role, String xmlName ) {
// TODO
if( role.equals("class") )
return convertToCamelNotation(xmlName,true);
if( role.equals("interface") )
return "I"+convertToCamelNotation(xmlName,true);
return convertToCamelNotation(xmlName,false);
}
/**
* converts a given string to the camel notation.
*/
private static String convertToCamelNotation( String name, boolean capitalizeFirstLetter ) {
StringBuffer r = new StringBuffer();
boolean capitalize = capitalizeFirstLetter;
int len = name.length();
for( int i=0; i=0 )
return true;
if( !isFirstChar
&& "1234567890".indexOf(ch)>=0 )
return true;
return false;
}
/**
* capitalizes the first character.
*/
public static String capitalizeFirst( String name ) {
return Character.toUpperCase(name.charAt(0))+name.substring(1);
}
}
msv-2009.1/tahiti/src/com/sun/tahiti/reader/relaxng/ 0000755 0001750 0001750 00000000000 11622453065 022444 5 ustar giovanni giovanni msv-2009.1/tahiti/src/com/sun/tahiti/reader/relaxng/TRELAXNGReader.java 0000644 0001750 0001750 00000024165 07363143557 025677 0 ustar giovanni giovanni /*
* @(#)$Id: TRELAXNGReader.java 1231 2001-10-16 23:49:03Z Bear $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.tahiti.reader.relaxng;
import com.sun.msv.grammar.*;
import com.sun.msv.datatype.DatabindableDatatype;
import com.sun.msv.reader.trex.ng.RELAXNGReader;
import com.sun.msv.reader.ExpressionState;
import com.sun.msv.reader.GrammarReaderController;
import com.sun.msv.util.StartTagInfo;
import com.sun.tahiti.reader.annotator.Annotator;
import com.sun.tahiti.reader.NameUtil;
import com.sun.tahiti.reader.TahitiGrammarReader;
import com.sun.tahiti.grammar.*;
import javax.xml.parsers.SAXParserFactory;
import java.util.Map;
import java.util.Stack;
import java.util.ResourceBundle;
import java.text.MessageFormat;
import org.xml.sax.SAXException;
import org.xml.sax.Attributes;
/**
* parses Tahiti-annotated RELAX NG grammar.
*
* @author
* Kohsuke KAWAGUCHI
*/
public class TRELAXNGReader extends RELAXNGReader implements TahitiGrammarReader {
public TRELAXNGReader(
GrammarReaderController controller, SAXParserFactory parserFactory,
StateFactory stateFactory, ExpressionPool pool ) {
super( controller, parserFactory, stateFactory, pool );
}
public TRELAXNGReader(
GrammarReaderController controller, SAXParserFactory parserFactory ) {
super( controller, parserFactory );
}
private final AnnotatedGrammar annGrammar = new AnnotatedGrammar( null, pool );
public AnnotatedGrammar getAnnotatedResult() {
return annGrammar;
}
protected Expression interceptExpression( ExpressionState state, Expression exp ) {
// if an error was found, stop processing.
if( hadError ) return exp;
// check Tahiti attributes.
final StartTagInfo tag = state.getStartTag();
String role = tag.getAttribute(TahitiNamespace,"role");
if( role==null ) {
// there is no markup.
// insert an ClassItem if this is the tag.
// some of those temporarily added ClassItems will be removed
// in the final wrap up.
if( tag.localName.equals("element") ) {
// if( exp instanceof ElementExp ) {
/*
ElementExp eexp = (ElementExp)exp;
// add a ClassItem between the ElementExp and the content model.
ClassItem t = annGrammar.createClassItem( decideName(state,exp,"class"), eexp.contentModel );
eexp.contentModel = t;
t.isTemporary = true; // this flag indicates that this class item is a temporary one.
return eexp;
*/
// to make marshalling easy, ClassItem is generated above the ElementExp
// calculate the unique name to avoid name conflicts.
String baseName = decideName(state,exp,"class");
if( annGrammar.classes.containsKey(baseName) ) {
int cnt = 2;
while( annGrammar.classes.containsKey(baseName+cnt) )
cnt++;
baseName += cnt;
}
ClassItem t = annGrammar.createClassItem( baseName, exp );
t.isTemporary = true;
return t;
} else {
// if this element has the t:name attribute, store that
// information by using a ReferenceExp. This information
// might be useful to various annotators.
// String name = tag.getAttribute(TahitiNamespace,"name");
// if(name!=null) exp = new ReferenceExp( name, exp );
}
return exp; // the "role" attribute is not present.
}
OtherExp roleExp;
if( role.equals("none") ) {
// do nothing. this will prevent automatic ClassItem insertion.
return exp;
} else
if( role.equals("superClass") ) {
roleExp = new SuperClassItem();
} else
if( role.equals("class") ) {
/*
removes silly use of temporary ClassItem.
Consider the following grammar fragment:
...
Since there is no tahiti markup for element, a temporary ClassItem
is inserted. Immediately after that, a element is processed, and
a new ClassItem is inserted.
The following code is a quick hack to prevent this situation by removing
temporary ClassItem if it is the immediate child of the user-defined class.
*/
/*
We changed the code and now temporary class items are generated
*above* elements. So now this code is unnecessary.
*/
/* TODO:
we have to think in much broader view.
This could be done as a part of temporary class item removal.
Otherwise, we have to implement this mechanism to every reader.
Also, this particular situation would interact with the combine attribute.
*/
/* if( (exp instanceof ClassItem) && ((ClassItem)exp).isTemporary )
exp = ((ClassItem)exp).exp;
if( exp.getClass()==ReferenceExp.class ) {
ReferenceExp rexp = (ReferenceExp)exp;
if( (rexp.exp instanceof ClassItem) && ((ClassItem)rexp.exp).isTemporary )
rexp.exp = ((ClassItem)rexp.exp).exp;
}
*/
roleExp = annGrammar.createClassItem(decideName(state,exp,role),null);
} else
if( role.equals("field") ) {
FieldItem fi = new FieldItem(decideName(state,exp,role));
roleExp = fi;
// read the additional configuration.
String collection = tag.getAttribute(TahitiNamespace,"collection");
if(collection!=null) {
fi.collectionType = fi.collectionType.parse(collection);
if(fi.collectionType==null)
reportError( ERR_INVALID_COLLECTION_TYPE, collection );
}
String access = tag.getAttribute(TahitiNamespace,"access");
if(access!=null) {
fi.accessModifier = fi.accessModifier.parse(access);
if(fi.accessModifier==null)
reportError( ERR_INVALID_ACCESS_MODIFIER, access );
}
String method = tag.getAttribute(TahitiNamespace,"method");
if(method!=null) {
fi.accessor = fi.accessor.parse(method);
if(fi.accessModifier==null)
reportError( ERR_INVALID_ACCESSOR, method );
}
} else
if( role.equals("interface") ) {
roleExp = annGrammar.createInterfaceItem(decideName(state,exp,role),null);
} else
if( role.equals("ignore") ) {
roleExp = new IgnoreItem();
} else {
reportError( ERR_UNDEFINED_ROLE, role );
return exp;
}
setDeclaredLocationOf(roleExp); // memorize where this expression is defined.
if( tag.localName.equals("define") ) {
// if this is , then
// this tag should be placed as the sole child of .
ReferenceExp rexp = (ReferenceExp)exp;
roleExp.exp = rexp.exp;
rexp.exp = roleExp;
} else {
// wrap the expression by this tag.
roleExp.exp = exp;
exp = roleExp;
}
return exp;
}
/**
* compute the name for the item.
*
* @param role
* the role of this expression. One of "field","interface", and "class".
*/
protected String decideName( ExpressionState state, Expression exp, String role ) {
final StartTagInfo tag = state.getStartTag();
String name = tag.getAttribute(TahitiNamespace,"name");
// if we have t:name attribute, use it.
if(name==null) {
// if the current tag has the name attribute, use it.
// this is the case of ,, and sometimes
// and
name = tag.getAttribute("name");
if(name!=null) name = NameUtil.xmlNameToJavaName(role,name);
}
if(name==null) {
// otherwise, sniff the name.
// if it's element/attribute, then we may be able to use its name.
if( exp instanceof NameClassAndExpression ) {
NameClass nc = ((NameClassAndExpression)exp).getNameClass();
if( nc instanceof SimpleNameClass )
name = NameUtil.xmlNameToJavaName(role,((SimpleNameClass)nc).localName);
// if it's not a simple type, abort.
}
}
if(name==null) {
// we can't generate a proper name. bail out
reportError( ERR_NAME_NEEDED );
return "";
}
if( role.equals("class") || role.equals("interface") ) {
// append the default package name, if necessary.
int idx = name.indexOf('.');
if(idx<0 && defaultPackageName.length()!=0 )
name = defaultPackageName+"."+name;
}
return name;
}
public void wrapUp() {
// First, let the super class do its job.
super.wrapUp();
// if we already have an error, abort further processing.
if(hadError) return;
// if no package name is specified, place it to the root pacakge.
if(annGrammar.grammarName==null)
annGrammar.grammarName = "Grammar";
// add missing annotations and normalizes them.
annGrammar.topLevel = grammar.exp;
Annotator.annotate( annGrammar, this );
grammar.exp = annGrammar.topLevel;
}
/**
* propagatable 't:package' attribute that specifies the default package
* for unqualified java classes/interfaces.
*/
private final Stack packageNameStack = new Stack();
private String defaultPackageName="";
public void startElement( String a, String b, String c, Attributes d ) throws SAXException {
// handle "t:package" attribute here.
packageNameStack.push(defaultPackageName);
if( d.getIndex(TahitiNamespace,"package")!=-1 ) {
defaultPackageName = d.getValue(TahitiNamespace,"package");
// if this is the first time the package name is specified,
// then use it for the grammar's name.
if(annGrammar.grammarName==null)
annGrammar.grammarName = defaultPackageName+".Grammar";
}
super.startElement(a,b,c,d);
}
public void endElement( String a, String b, String c ) throws SAXException {
super.endElement(a,b,c);
defaultPackageName = (String)packageNameStack.pop();
}
protected String localizeMessage( String propertyName, Object[] args ) {
String format;
try {
format = ResourceBundle.getBundle(
"com.sun.tahiti.reader.relaxng.Messages").getString(propertyName);
} catch( Exception e ) {
try {
format = ResourceBundle.getBundle(
"com.sun.tahiti.reader.Messages").getString(propertyName);
} catch( Exception ee ) {
return super.localizeMessage(propertyName,args);
}
}
return MessageFormat.format(format, args );
}
// TODO: add more arguments to produce user-friendly messages.
public static final String ERR_UNDEFINED_ROLE = // arg:1
"UndefinedRole"; // "{0}" is a bad value for the role attribute.
public static final String ERR_NAME_NEEDED = // arg:0
"NameNeeded"; // failed to generate a proper name for this role.
// specify t:name attribute.
}
msv-2009.1/tahiti/src/com/sun/tahiti/reader/relaxng/Messages.properties 0000644 0001750 0001750 00000000234 07315754631 026337 0 ustar giovanni giovanni
UndefinedRole = \
"{0}" is a bad value for the role attribute.
NameNeeded = \
failed to generate a proper name for this role. specify t:name attribute.
msv-2009.1/tahiti/src/com/sun/tahiti/grammar/ 0000755 0001750 0001750 00000000000 11622453065 021170 5 ustar giovanni giovanni msv-2009.1/tahiti/src/com/sun/tahiti/grammar/SystemType.java 0000644 0001750 0001750 00000003344 07326114117 024163 0 ustar giovanni giovanni /*
* @(#)$Id: SystemType.java 923 2001-07-20 20:45:03Z Bear $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.tahiti.grammar;
import java.util.Map;
/**
* built-in types.
*
* @author
* Kohsuke KAWAGUCHI
*/
public class SystemType implements Type {
/**
* this map is from java/lang/Class objects to the corresponding SystemType object.
* Ssed to unify the system types.
*/
private static Map systemTypes = new java.util.HashMap();
/** gets the SystemType object that corresponds to the specified type. */
public static synchronized SystemType get( Class c ) {
SystemType t = (SystemType)systemTypes.get(c);
if(t==null)
systemTypes.put(c, t=new SystemType(c));
return t;
}
private SystemType( Class c ) {
this.theClass = c;
}
/** Class object which this object is representing. */
private final Class theClass;
public Type getSuperType() {
Class su = theClass.getSuperclass();
if(su==null) return null;
else return get(su);
}
public String getTypeName() {
return theClass.getName();
}
public String getPackageName() {
String name = getTypeName();
int idx = name.lastIndexOf('.');
if(idx<0) return null;
else return name.substring(0,idx);
}
public String getBareName() {
String name = getTypeName();
int idx = name.lastIndexOf('.');
if(idx<0) return name;
else return name.substring(idx+1);
}
public Type[] getInterfaces() {
Class[] is = theClass.getInterfaces();
Type[] r = new Type[is.length];
for( int i=0; iKohsuke KAWAGUCHI
*/
public class InterfaceItem extends TypeItem {
protected InterfaceItem( String name, Expression body ) {
super(name);
this.exp = body;
}
public Type getSuperType() { return null; } // interfaces do not have the super type.
public Object visitJI( JavaItemVisitor visitor ) {
return visitor.onInterface(this);
}
}
msv-2009.1/tahiti/src/com/sun/tahiti/grammar/FieldUse.java 0000644 0001750 0001750 00000005353 07337072463 023550 0 ustar giovanni giovanni /*
* @(#)$Id: FieldUse.java 1081 2001-08-17 01:36:51Z Bear $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.tahiti.grammar;
import java.util.Set;
import java.util.Iterator;
import com.sun.tahiti.grammar.util.Multiplicity;
/**
* aggregated field information.
*
* Information about one field can be possibly spanned across
* multiple FieldItems. This object serves as a bundle of those FieldItems
* that share the same name.
*
* @author
* Kohsuke KAWAGUCHI
*/
public class FieldUse {
public FieldUse( String name ) {
this.name = name;
}
/** field name */
public final String name;
/**
* item type of this field.
* For example, if this field is a set of Object then this field is set to 'Object'.
* This field is computed in the 2nd pass.
*/
public Type type;
/**
* computes the value of the accessor of this field.
*/
public Accessor getAccessor() {
// use the first one found.
// this means that if two different things are specified,
// one will be ignored and we cannot tell which one is ignored.
Iterator itr = items.iterator();
while(itr.hasNext()) {
Accessor acc = ((FieldItem)itr.next()).accessor;
if( acc!=null ) return acc;
}
return Accessor.getDefault();
}
/**
* computes the value of the access modifier of this field.
*/
public AccessModifier getAccessModifier() {
// use the first one found.
// this means that if two different things are specified,
// one will be ignored and we cannot tell which one is ignored.
Iterator itr = items.iterator();
while(itr.hasNext()) {
AccessModifier acc = ((FieldItem)itr.next()).accessModifier;
if( acc!=null ) return acc;
}
return AccessModifier.getDefault();
}
/**
* computes the value of the collection type of this field.
*/
public CollectionType getCollectionType() {
// use the first one found.
// this means that if two different things are specified,
// one will be ignored and we cannot tell which one is ignored.
Iterator itr = items.iterator();
while(itr.hasNext()) {
CollectionType acc = ((FieldItem)itr.next()).collectionType;
if( acc!=null ) return acc;
}
return CollectionType.getDefault();
}
/**
* set of FieldItems that shares the same name.
* This field is computed in the 1st pass.
*/
public final Set items = new java.util.HashSet();
public FieldItem[] getItems() {
return (FieldItem[])items.toArray(new FieldItem[0]);
}
/**
* total multiplicity from the parent class to items of this field.
* This field is computed in the 2nd pass.
*/
public Multiplicity multiplicity;
}
msv-2009.1/tahiti/src/com/sun/tahiti/grammar/CollectionType.java 0000644 0001750 0001750 00000001526 07337072463 025003 0 ustar giovanni giovanni package com.sun.tahiti.grammar;
public class CollectionType {
/** no need to create an instance. Use predefined values. */
private CollectionType() {}
public static CollectionType set = new CollectionType();
public static CollectionType list = new CollectionType();
public static CollectionType vector = new CollectionType();
public static CollectionType getDefault() {
return list;
}
/**
* parses the string representation of the collection type
* and returns one of the predefined value.
*
* @return
* If the value is not recognized, return null.
*/
public static CollectionType parse( String value ) {
value = value.trim();
if(value.equalsIgnoreCase("set")) return set;
if(value.equalsIgnoreCase("list")) return list;
if(value.equalsIgnoreCase("vector")) return vector;
return null; // unrecognized
}
}
msv-2009.1/tahiti/src/com/sun/tahiti/grammar/JavaItem.java 0000644 0001750 0001750 00000001322 07337343356 023542 0 ustar giovanni giovanni /*
* @(#)$Id: JavaItem.java 1087 2001-08-18 01:37:50Z Bear $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.tahiti.grammar;
import com.sun.msv.grammar.OtherExp;
/**
* the base class of all special OtherExps
* that are used to annotate tahiti data-binding information
* to AGM.
*
* @author
* Kohsuke KAWAGUCHI
*/
public abstract class JavaItem extends OtherExp {
public JavaItem( String name ) {
this.name = name;
}
public String name;
public abstract Object visitJI( JavaItemVisitor visitor );
}
msv-2009.1/tahiti/src/com/sun/tahiti/grammar/AnnotatedGrammar.java 0000644 0001750 0001750 00000006530 07337343356 025274 0 ustar giovanni giovanni /*
* @(#)$Id: AnnotatedGrammar.java 1087 2001-08-18 01:37:50Z Bear $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.tahiti.grammar;
import com.sun.msv.grammar.Expression;
import com.sun.msv.grammar.ExpressionPool;
import com.sun.msv.grammar.Grammar;
import java.util.Map;
import java.util.Collection;
import java.util.Iterator;
/**
* An AGM with Tahiti annotation.
*
* This object keeps track of all JavaItems added to the grammar.
*
* @author
* Kohsuke KAWAGUCHI
*/
public final class AnnotatedGrammar implements Grammar
{
/**
* creates an instance by copying values from the specified grammar.
*/
public AnnotatedGrammar( Grammar source ) {
this( source.getTopLevel(), source.getPool() );
}
public AnnotatedGrammar( Expression topLevel, ExpressionPool pool ) {
this.topLevel = topLevel;
this.pool = pool;
}
public Expression topLevel;
public Expression getTopLevel() { return topLevel; }
private final ExpressionPool pool;
public ExpressionPool getPool() { return pool; }
/**
* the grammar file will be generated as this name.
* This field would be something like "com.example.abc.FileName".
* It shouldn't have a file extension.
*
* This field must be set by the reader.
*/
public String grammarName;
/** all ClassItems in this grammar (from the fully qualified name to ClassItem). */
public final Map classes = new java.util.HashMap();
public ClassItem[] getClasses() {
return (ClassItem[])classes.values().toArray( new ClassItem[classes.size()] );
}
public Iterator iterateClasses() {
return classes.values().iterator();
}
/** all InterfaceItems in this grammar (from the fully qualified name to InterfaceItem). */
public final Map interfaces = new java.util.HashMap();
public InterfaceItem[] getInterfaces() {
return (InterfaceItem[])interfaces.values().toArray( new InterfaceItem[interfaces.size()] );
}
public Iterator iterateInterfaces() {
return interfaces.values().iterator();
}
/** creates a new ClassItem. */
public ClassItem createClassItem( String typeFullName, Expression body ) {
// type name must be unique.
assert(!classes.containsKey(typeFullName));
ClassItem o = new ClassItem(typeFullName,body);
classes.put(typeFullName,o);
return o;
}
/** creates a new InterfaceItem. */
public InterfaceItem createInterfaceItem( String typeFullName, Expression body ) {
// type name must be unique.
assert(!interfaces.containsKey(typeFullName));
InterfaceItem o = new InterfaceItem(typeFullName,body);
interfaces.put(typeFullName,o);
return o;
}
/** removes a ClassItem. */
public void removeClassItem( ClassItem c ) {
// only a temporary class item can be removed.
// DBG
if(!c.isTemporary) {
System.out.println(com.sun.msv.grammar.util.ExpressionPrinter.printContentModel(c));
System.out.println(c.getTypeName());
}
assert(c.isTemporary);
assert(classes.containsValue(c));
classes.remove(c.name);
}
public void removeClassItems( Collection col ) {
Object[] o = col.toArray();
for( int i=0; i
* Also keeps the information about how accessor should be generated.
*
* @author
* Kohsuke KAWAGUCHI
*/
public class FieldItem extends JavaItem {
public FieldItem( String name ) {
super(name);
}
public FieldItem( String name, Expression exp ) {
this(name);
this.exp = exp;
}
/** specified accessor value. If none is specified by the user, null. */
public Accessor accessor;
/** specified access modifier value. If none is specified by the user, null. */
public AccessModifier accessModifier;
/** specified collection type. If none is specified by the user, null. */
public CollectionType collectionType;
/**
* multiplicity of this field to its children (field-class/interface).
* Note that this multiplicity and class-field multiplicity is completely
* a different thing.
*
* This field is computed during the first pass of the normalization.
*/
public Multiplicity multiplicity;
/**
* all Types that can appear as the children of this type.
* This field is computed during the first pass of the normalization.
*/
public final Set types = new java.util.HashSet();
public Object visitJI( JavaItemVisitor visitor ) {
return visitor.onField(this);
}
}
msv-2009.1/tahiti/src/com/sun/tahiti/grammar/Accessor.java 0000644 0001750 0001750 00000002275 07337072463 023612 0 ustar giovanni giovanni /*
* @(#)$Id: Accessor.java 1081 2001-08-17 01:36:51Z Bear $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.tahiti.grammar;
/**
*
*
* @author
* Kohsuke KAWAGUCHI
*/
public class Accessor {
/**
* no need to create an instance.
* Use pre-defined values.
*/
private Accessor() {}
public static Accessor field = new Accessor();
public static Accessor readOnly = new Accessor();
public static Accessor readWrite = new Accessor();
/** gets the default accessor. */
public static Accessor getDefault() {
return readWrite;
}
/**
* parses the string representation of the accessor
* and returns one of the predefined value.
*
* @return
* If the value is not recognized, return null.
*/
public static Accessor parse( String value ) {
value = value.trim();
if(value.equalsIgnoreCase("field")) return field;
if(value.equalsIgnoreCase("readOnly")) return readOnly;
if(value.equalsIgnoreCase("readWrite")) return readWrite;
return null; // unrecognized
}
}
msv-2009.1/tahiti/src/com/sun/tahiti/grammar/util/ 0000755 0001750 0001750 00000000000 11622453065 022145 5 ustar giovanni giovanni msv-2009.1/tahiti/src/com/sun/tahiti/grammar/util/NotAllowedRemover.java 0000644 0001750 0001750 00000004374 07327153236 026434 0 ustar giovanni giovanni /*
* @(#)$Id: NotAllowedRemover.java 937 2001-07-24 01:59:58Z Bear $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.tahiti.grammar.util;
import com.sun.msv.grammar.*;
import java.util.Set;
/**
* completely removes <notAllowed /> from the grammar.
*
* The ExpressionPool class does a reasonable job to remove <notAllowed/>.
* For example, the createSequence method returns Expression.nullSet if one of the
* parameter is the nullSet.
*
* However, it cannot remove elements/attributes whose content model is the nullSet,
* nor can it remove ReferenceExps whose body is the nullSet. This class walks the
* grammar and removes those unused ReferenceExps, elements, and attributes.
*
* @author
* Kohsuke KAWAGUCHI
*/
public class NotAllowedRemover extends ExpressionCloner {
public NotAllowedRemover( ExpressionPool pool ) {
super(pool);
}
public Expression onRef( ReferenceExp exp ) {
Expression body = exp.exp.visit(this);
if(body==Expression.nullSet)
return Expression.nullSet;
exp.exp=body;
return exp;
}
public Expression onOther( OtherExp exp ) {
Expression body = exp.exp.visit(this);
if(body==Expression.nullSet)
return Expression.nullSet;
exp.exp=body;
return exp;
}
/**
* this set keeps the visited ElementExps/AttributeExps, to prevent
* infinite recursion.
*/
private final Set visitedExps = new java.util.HashSet();
public Expression onElement( ElementExp exp ) {
if( !visitedExps.add(exp) )
return exp; // this ElementExp is already processed.
Expression body = exp.contentModel.visit(this);
if( body==Expression.nullSet )
return Expression.nullSet;
exp.contentModel=body;
return exp;
}
public Expression onAttribute( AttributeExp exp ) {
if( !visitedExps.add(exp) )
return exp; // this AttributeExp is already processed.
Expression body = exp.exp.visit(this);
if( body==Expression.nullSet )
return Expression.nullSet;
return pool.createAttribute( exp.nameClass, body );
}
private static void assert( boolean b ) {
if(!b) throw new Error();
}
}
msv-2009.1/tahiti/src/com/sun/tahiti/grammar/util/Multiplicity.java 0000644 0001750 0001750 00000005322 07337072463 025511 0 ustar giovanni giovanni /*
* @(#)$Id: Multiplicity.java 1081 2001-08-17 01:36:51Z Bear $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.tahiti.grammar.util;
import com.sun.msv.grammar.Expression;
/**
* represents a possible number of occurence.
*
* Usually, denoted by a pair of integers like (1,1) or (5,10).
* A special value "unbounded" is allowed as the upper bound.
*
*
* For example, (0,unbounded) corresponds to the '*' occurence of DTD.
* (0,1) corresponds to the '?' occurence of DTD.
*
* @author
* Kohsuke KAWAGUCHI
*/
public class Multiplicity {
public final int min;
public final Integer max; // null is used to represent "unbounded".
public Multiplicity( int min, Integer max ) {
this.min = min; this.max = max;
}
public Multiplicity( int min, int max ) {
this.min = min; this.max = new Integer(max);
}
/** returns true if the multiplicity is (1,1). */
public boolean isUnique() {
if(max==null) return false;
return min==1 && max.intValue()==1;
}
/** returns true if the multiplicity is (0,1) or (1,1). */
public boolean isAtMostOnce() {
if(max==null) return false;
return max.intValue()<=1;
}
/** returns true if the multiplicity is (0,0). */
public boolean isZero() {
if(max==null) return false;
return max.intValue()==0;
}
/** gets the string representation.
* mainly debug purpose.
*/
public String toString() {
return "("+(max==null?"unbounded":max.toString())+","+min+")";
}
/** the constant representing the (0,0) multiplicity. */
public static Multiplicity zero = new Multiplicity(0,0);
/** the constante representing the (1,1) multiplicity. */
public static Multiplicity one = new Multiplicity(1,1);
public static Multiplicity calc( Expression exp, MultiplicityCounter calc ) {
return (Multiplicity)exp.visit(calc);
}
// arithmetic methods
//============================
public static Multiplicity choice( Multiplicity lhs, Multiplicity rhs ) {
return new Multiplicity(
Math.min(lhs.min,rhs.min),
(lhs.max==null||rhs.max==null)?
null:
new Integer(Math.max(lhs.max.intValue(),rhs.max.intValue())) );
}
public static Multiplicity group( Multiplicity lhs, Multiplicity rhs ) {
return new Multiplicity( lhs.min+rhs.min,
(lhs.max==null||rhs.max==null)?
null:
new Integer(lhs.max.intValue()+rhs.max.intValue()) );
}
public static Multiplicity oneOrMore( Multiplicity c ) {
if(c.max==null) return c; // (x,*) => (x,*)
if(c.max.intValue()==0 ) return c; // (0,0) => (0,0)
else return new Multiplicity( c.min, null ); // (x,y) => (x,*)
}
}
msv-2009.1/tahiti/src/com/sun/tahiti/grammar/util/MultiplicityCounter.java 0000644 0001750 0001750 00000007277 07365333167 027066 0 ustar giovanni giovanni /*
* @(#)$Id: MultiplicityCounter.java 1256 2001-10-23 18:27:03Z Bear $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.tahiti.grammar.util;
import com.sun.msv.grammar.*;
import com.sun.tahiti.grammar.*;
/**
* visits an expression and computes the multiplicity of the designated child item.
*
* Note that currently this method does not do anything to stop infinite recursion.
* The algorithm should be implemented within this class to handle recursive multiplicity
* calculation.
*
* @author
* Kohsuke KAWAGUCHI
*/
public abstract class MultiplicityCounter implements ExpressionVisitor
{
/**
* computes the multiplicity of child Java items.
*/
public static final MultiplicityCounter javaItemCounter =
new MultiplicityCounter(){
protected Multiplicity isChild( Expression exp ) {
if(exp instanceof IgnoreItem) return Multiplicity.zero;
if(exp instanceof JavaItem) return Multiplicity.one;
else return null;
}
};
/**
* this method should be implemented for this class to work correctly.
* If the specified expression is a designated child item, then
* return its multiplicity. Otherwise return null.
*/
protected abstract Multiplicity isChild( Expression exp );
public Object onSequence( SequenceExp exp ) {
Multiplicity m = isChild(exp);
if(m!=null) return m;
return Multiplicity.group(
(Multiplicity)exp.exp1.visit(this),
(Multiplicity)exp.exp2.visit(this)
);
}
public Object onInterleave( InterleaveExp exp ) {
Multiplicity m = isChild(exp);
if(m!=null) return m;
return Multiplicity.group(
(Multiplicity)exp.exp1.visit(this),
(Multiplicity)exp.exp2.visit(this)
);
}
public Object onChoice( ChoiceExp exp ) {
Multiplicity m = isChild(exp);
if(m!=null) return m;
return Multiplicity.choice(
(Multiplicity)exp.exp1.visit(this),
(Multiplicity)exp.exp2.visit(this)
);
}
public Object onOneOrMore( OneOrMoreExp exp ) {
Multiplicity m = isChild(exp);
if(m!=null) return m;
return Multiplicity.oneOrMore( (Multiplicity)exp.exp.visit(this) );
}
public Object onMixed( MixedExp exp ) {
Multiplicity m = isChild(exp);
if(m!=null) return m;
return exp.exp.visit(this);
}
public Object onList( ListExp exp ) {
Multiplicity m = isChild(exp);
if(m!=null) return m;
return exp.exp.visit(this);
}
public Object onEpsilon() {
Multiplicity m = isChild(Expression.epsilon);
if(m==null) m=Multiplicity.zero;
return m;
}
public Object onAnyString() {
Multiplicity m = isChild(Expression.anyString);
if(m==null) m=Multiplicity.zero;
return m;
}
public Object onData( DataExp exp ) {
Multiplicity m = isChild(exp);
if(m==null) m=Multiplicity.zero;
return m;
}
public Object onValue( ValueExp exp ) {
Multiplicity m = isChild(exp);
if(m==null) m=Multiplicity.zero;
return m;
}
public Object onElement( ElementExp exp ) {
Multiplicity m = isChild(exp);
if(m!=null) return m;
return exp.contentModel.visit(this);
}
public Object onAttribute( AttributeExp exp ) {
Multiplicity m = isChild(exp);
if(m!=null) return m;
return exp.exp.visit(this);
}
public Object onRef( ReferenceExp exp ) {
Multiplicity m = isChild(exp);
if(m!=null) return m;
return exp.exp.visit(this);
}
public Object onOther( OtherExp exp ) {
Multiplicity m = isChild(exp);
if(m!=null) return m;
return exp.exp.visit(this);
}
// assertions. these method may never be called.
public Object onConcur( ConcurExp exp ) { throw new Error(); }
public Object onNullSet() { throw new Error(); }
}
msv-2009.1/tahiti/src/com/sun/tahiti/grammar/util/SuperClassBodyRemover.java 0000644 0001750 0001750 00000010642 07330362535 027257 0 ustar giovanni giovanni /*
* @(#)$Id: SuperClassBodyRemover.java 971 2001-07-27 22:04:13Z Bear $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.tahiti.grammar.util;
import com.sun.msv.grammar.*;
import com.sun.msv.grammar.trex.ElementPattern;
import com.sun.msv.grammar.util.ExpressionWalker;
import com.sun.tahiti.grammar.*;
import java.util.Set;
/**
* removes ClassItem inside SuperClassItem as a preparation
* of the marshaller generation.
*
*
* Care has to be taken not to remove ClassItems directly referenced
* from other part of the grammar. For example,
*
*
*
* @author
* Kohsuke KAWAGUCHI
*/
public class SuperClassBodyRemover extends ExpressionCloner {
private final Set visitedRefs = new java.util.HashSet();
public static void remove( AnnotatedGrammar g ) {
SuperClassBodyRemover su = new SuperClassBodyRemover(g.getPool());
ClassItem[] cls = g.getClasses();
for( int i=0; i
We cannot strip the ClassItem of the "base" correctly unless
we copy the definition of the "body" elment.
*/
public Expression onAttribute( AttributeExp exp ) {
return super.pool.createAttribute(exp.nameClass,exp.exp.visit(this));
}
public Expression onElement( ElementExp exp ) {
Expression body = exp.contentModel.visit(this);
if(body==exp.contentModel) return exp; // this item is not modified.
else
// body of this element is modified.
// since this ElementExp might be shared,
// we need to create a fresh ElementExp.
return new ElementPattern(exp.getNameClass(),body);
}
};
}
}
msv-2009.1/tahiti/src/com/sun/tahiti/grammar/PrimitiveItem.java 0000644 0001750 0001750 00000003325 07337072463 024634 0 ustar giovanni giovanni /*
* @(#)$Id: PrimitiveItem.java 1081 2001-08-17 01:36:51Z Bear $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.tahiti.grammar;
import com.sun.msv.grammar.Expression;
import com.sun.msv.datatype.DatabindableDatatype;
import java.util.Set;
/**
* represents a "primitive" type.
*
* Primitive types are those types which can construct itself from a string
* and a DataType.
*
* @author
* Kohsuke KAWAGUCHI
*/
public class PrimitiveItem extends JavaItem implements Type {
public PrimitiveItem( DatabindableDatatype dt ) {
super(calcType(dt).getName());
this.type = SystemType.get(calcType(dt));
this.dt = dt;
}
public PrimitiveItem( DatabindableDatatype type, Expression exp ) {
this(type);
this.exp = exp;
}
private static Class calcType( DatabindableDatatype dt ) {
if(dt==null) return String.class;
else return dt.getJavaObjectType();
}
/**
* actual type. This object works as a proxy to this field
*/
public final SystemType type;
/**
* underlying datatype object.
* This field is null if the underlying datatype is not databindable.
*/
public final DatabindableDatatype dt;
public String getTypeName() { return type.getTypeName(); }
public Type[] getInterfaces() { return type.getInterfaces(); }
public Type getSuperType() { return type.getSuperType(); }
public String getPackageName() { return type.getPackageName(); }
public String getBareName() { return type.getBareName(); }
public Object visitJI( JavaItemVisitor visitor ) {
return visitor.onPrimitive(this);
}
}
msv-2009.1/tahiti/src/com/sun/tahiti/grammar/SuperClassItem.java 0000644 0001750 0001750 00000001476 07326165562 024756 0 ustar giovanni giovanni /*
* @(#)$Id: SuperClassItem.java 930 2001-07-21 02:39:46Z Bear $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.tahiti.grammar;
import com.sun.msv.grammar.Expression;
/**
* represents a derivation relationship between two classes.
*
* @author
* Kohsuke KAWAGUCHI
*/
public class SuperClassItem extends JavaItem {
public SuperClassItem() {
super("superClass-marker");
}
public SuperClassItem( Expression exp ) {
this();
this.exp=exp;
}
/** actual super class definition. */
public ClassItem definition = null;
public Object visitJI( JavaItemVisitor visitor ) {
return visitor.onSuper(this);
}
}
msv-2009.1/tahiti/src/com/sun/tahiti/grammar/ClassItem.java 0000644 0001750 0001750 00000002021 07326114117 023710 0 ustar giovanni giovanni /*
* @(#)$Id: ClassItem.java 923 2001-07-20 20:45:03Z Bear $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.tahiti.grammar;
import com.sun.msv.grammar.Expression;
/**
* represents a generated class.
*
* @author
* Kohsuke KAWAGUCHI
*/
public class ClassItem extends TypeItem {
protected ClassItem( String name, Expression exp ) {
super(name);
this.exp = exp;
}
/**
* this flag is set to true if this class item is generated by automatic guessing,
* rathen than the explicit instruction of the user.
*/
public boolean isTemporary = false;
/** super class definition, if any. */
public SuperClassItem superClass;
public Type getSuperType() {
if(superClass==null) return null;
return superClass.definition;
}
public Object visitJI( JavaItemVisitor visitor ) {
return visitor.onClass(this);
}
}
msv-2009.1/tahiti/src/com/sun/tahiti/grammar/JavaItemVisitor.java 0000644 0001750 0001750 00000001237 07326114117 025114 0 ustar giovanni giovanni /*
* @(#)$Id: JavaItemVisitor.java 923 2001-07-20 20:45:03Z Bear $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.tahiti.grammar;
/**
* visits JavaItem.
*
* @author
* Kohsuke KAWAGUCHI
*/
public interface JavaItemVisitor {
Object onClass( ClassItem item );
Object onField( FieldItem item );
Object onIgnore( IgnoreItem item );
Object onInterface( InterfaceItem item );
Object onPrimitive( PrimitiveItem item );
Object onSuper( SuperClassItem item );
}
msv-2009.1/tahiti/src/com/sun/tahiti/grammar/AccessModifier.java 0000644 0001750 0001750 00000003071 07337072463 024723 0 ustar giovanni giovanni /*
* @(#)$Id: AccessModifier.java 1081 2001-08-17 01:36:51Z Bear $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.tahiti.grammar;
/**
* represents the access modifier (public/protected/private).
*
*
* The toString method can be used to obtain the string
* representation of the access modifier.
*
* @author
* Kohsuke KAWAGUCHI
*/
public class AccessModifier {
/** no need to create an instance. Use predefined values. */
private AccessModifier( String name ) { this.name=name; }
private final String name;
public String toString() { return name; }
public static AccessModifier _public = new AccessModifier("public");
public static AccessModifier _protected = new AccessModifier("protected");
public static AccessModifier _private = new AccessModifier("private");
/** gets the default access modifier. */
public static AccessModifier getDefault() {
return _public;
}
/**
* parses the string representation of the access modifer
* and returns one of the predefined value.
*
* @return
* If the value is not recognized, return null.
*/
public static AccessModifier parse( String value ) {
value = value.trim();
if(value.equalsIgnoreCase("public")) return _public;
if(value.equalsIgnoreCase("protected")) return _protected;
if(value.equalsIgnoreCase("private")) return _private;
return null; // unrecognized
}
}
msv-2009.1/tahiti/src/com/sun/tahiti/grammar/Type.java 0000644 0001750 0001750 00000002140 07326114117 022747 0 ustar giovanni giovanni /*
* @(#)$Id: Type.java 923 2001-07-20 20:45:03Z Bear $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.tahiti.grammar;
import java.util.Set;
/**
* Type. Several types are generated, and several types are built-in (such as String.)
* Generated types are modeled by TypeItem. Built-in types are modeled by SystemType.
*
* @author
* Kohsuke KAWAGUCHI
*/
public interface Type {
/** gets the fully-qualified name of this type. */
String getTypeName();
/**
* gets the package name of this type.
* This method returns null if this class does not reside in any package.
*/
String getPackageName();
/** gets the bare type name (without the package name.) */
String getBareName();
/** gets the super class if any. Otherwise null. */
Type getSuperType();
/** gets directly implemented interfaces. */
Type[] getInterfaces();
/*
Is this method necessary?
*/
// boolean isInterface();
}
msv-2009.1/tahiti/src/com/sun/tahiti/grammar/TypeItem.java 0000644 0001750 0001750 00000002633 07326114117 023575 0 ustar giovanni giovanni /*
* @(#)$Id: TypeItem.java 923 2001-07-20 20:45:03Z Bear $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.tahiti.grammar;
import java.util.Set;
import java.util.Map;
/**
* base class of the generated type.
*
* @author
* Kohsuke KAWAGUCHI
*/
public abstract class TypeItem extends JavaItem implements Type {
public TypeItem( String name ) {
super(name);
// everyone inherites MarshallableObject
interfaces.add( SystemType.get(com.sun.tahiti.runtime.sm.MarshallableObject.class) );
}
public final Set interfaces = new java.util.HashSet();
/** a map of field name to FieldUse */
public final Map fields = new java.util.HashMap();
public FieldUse getFieldUse( String name ) {
FieldUse r = (FieldUse)fields.get(name);
if(r==null) fields.put(name,r=new FieldUse(name));
return r;
}
public String getTypeName() { return name; }
public Type[] getInterfaces() {
return (Type[])interfaces.toArray(new Type[interfaces.size()]);
}
public String getPackageName() {
int idx = name.lastIndexOf('.');
if(idx<0) return null;
else return name.substring(0,idx);
}
public String getBareName() {
int idx = name.lastIndexOf('.');
if(idx<0) return name;
else return name.substring(idx+1);
}
}
msv-2009.1/tahiti/src/com/sun/tahiti/grammar/IgnoreItem.java 0000644 0001750 0001750 00000001310 07326165562 024100 0 ustar giovanni giovanni /*
* @(#)$Id: IgnoreItem.java 930 2001-07-21 02:39:46Z Bear $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.tahiti.grammar;
import com.sun.msv.grammar.Expression;
/**
* used to denote the ignored part of the grammar.
*
* @author
* Kohsuke KAWAGUCHI
*/
public class IgnoreItem extends JavaItem {
public IgnoreItem() { super("$ignore"); }
public IgnoreItem( Expression exp ) {
this();
this.exp=exp;
}
public Object visitJI( JavaItemVisitor visitor ) {
return visitor.onIgnore(this);
}
}
msv-2009.1/tahiti/src/com/sun/tahiti/compiler/ 0000755 0001750 0001750 00000000000 11622453065 021354 5 ustar giovanni giovanni msv-2009.1/tahiti/src/com/sun/tahiti/compiler/java/ 0000755 0001750 0001750 00000000000 11622453065 022275 5 ustar giovanni giovanni msv-2009.1/tahiti/src/com/sun/tahiti/compiler/java/ListFieldSerializer.java 0000644 0001750 0001750 00000001331 07337076316 027057 0 ustar giovanni giovanni /*
* @(#)$Id: ListFieldSerializer.java 1082 2001-08-17 02:09:18Z Bear $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.tahiti.compiler.java;
import com.sun.tahiti.grammar.*;
/**
* serializes a collection field by using a Vector.
*
* @author
* Kohsuke KAWAGUCHI
*/
class ListFieldSerializer extends VectorFieldSerializer
{
ListFieldSerializer( ClassSerializer parent, FieldUse fu ) {
super(parent,fu);
}
String getTypeStr() {
return "java.util.LinkedList /* of " + parent.toPrintName(fu.type) +" */";
}
}
msv-2009.1/tahiti/src/com/sun/tahiti/compiler/java/FieldSerializer.java 0000644 0001750 0001750 00000011553 07337076316 026232 0 ustar giovanni giovanni /*
* @(#)$Id: FieldSerializer.java 1082 2001-08-17 02:09:18Z Bear $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.tahiti.compiler.java;
import org.w3c.dom.Element;
import java.io.PrintWriter;
import java.util.Map;
import java.text.MessageFormat;
import com.sun.tahiti.grammar.*;
import com.sun.tahiti.reader.NameUtil;
/**
* produces field-access related java soure code.
*
* @author
* Kohsuke KAWAGUCHI
*/
abstract class FieldSerializer {
/**
* gets the appropriate field serializer for the specified FieldUse.
*/
public static FieldSerializer get( ClassSerializer parent, FieldUse fu ) {
if( fu.multiplicity.isUnique() && boxTypes.containsKey(fu.type.getTypeName()) )
// use the unboxed type.
return new PrimitiveTypeFieldSerializer(parent,fu);
if( fu.multiplicity.isAtMostOnce() )
// use item type itself.
return new AtmostOneFieldSerializer(parent,fu);
CollectionType t = fu.getCollectionType();
if(t==t.list) return new ListFieldSerializer(parent,fu);
if(t==t.set) return new SetFieldSerializer(parent,fu);
if(t==t.vector) return new VectorFieldSerializer(parent,fu);
// assertion failed
throw new Error("unrecognized collection type:"+t);
}
public FieldSerializer( ClassSerializer parent, FieldUse fu ) {
this.fu = fu;
this.parent = parent;
capitalizedFieldName = NameUtil.xmlNameToJavaName( "class", fu.name );
}
/** this serializer works on this object. */
protected final FieldUse fu;
/** the parent ClassSerializer object which owns this object. */
protected final ClassSerializer parent;
protected final String capitalizedFieldName;
/** gets the string that represents the type of the field. */
abstract String getTypeStr();
// /** gets the initializer of the field. */
// String getInitializer();
/**
* gets the string that will be used to add (or store) an object
* to the field.
*/
abstract String setField( String objName );
/**
* writes the field definition and accessors to the specified stream.
*/
final void writeFieldDef( PrintWriter out ) {
Accessor acc = fu.getAccessor();
AccessModifier mod = fu.getAccessModifier();
// if the accessor methods are going to be produced,
// produce a private field.
if(acc==acc.field) writeVariableDef(out,mod);
else writeVariableDef(out,mod._private);
if(acc!=acc.field) {
writeGetterDef(out,mod);
if(acc==acc.readWrite)
writeSetterDef(out,mod);
}
}
/**
* writes the bare field definition to the specified output object
* by using the specified access modifier.
*/
abstract void writeVariableDef( PrintWriter out, AccessModifier mod );
/**
* writes the getter method definition by using the specified access modifier.
*/
abstract void writeGetterDef( PrintWriter out, AccessModifier mod );
/**
* writes the setter method definition by using the specified access modifier.
*/
abstract void writeSetterDef( PrintWriter out, AccessModifier mod );
//
// marshaller related methods
//
/**
* produces a code fragment that creates an iterator, if necessary.
* @return null
* if this field doesn't need an initializer.
*/
abstract String marshallerInitializer();
/**
* produces a code fragment that checks the availability of the next token
* of this field.
*/
abstract String hasMoreToken();
/**
* produces a code to marshall the next token of this field, and consumes
* that token.
*
* @param marshallElement
*
*/
abstract String marshall( Element marshallElement );
/**
* Java objects which has the corresponding built-in type.
*/
protected static final Map boxTypes;
static {
boxTypes = new java.util.HashMap();
boxTypes.put( "java.lang.Integer", "int" );
boxTypes.put( "java.lang.Boolean", "boolean" );
boxTypes.put( "java.lang.Double", "double" );
boxTypes.put( "java.lang.Float", "float" );
boxTypes.put( "java.lang.Char", "char" );
boxTypes.put( "java.lang.Long", "long" );
boxTypes.put( "java.lang.Byte", "byte" );
boxTypes.put( "java.lang.Short", "short" );
}
protected static String format( String fmt, Object[] args ) {
return MessageFormat.format(fmt,args);
}
protected static String format( String fmt, Object arg1 ) {
return MessageFormat.format(fmt,new Object[]{arg1});
}
protected static String format( String fmt, Object arg1, Object arg2 ) {
return MessageFormat.format(fmt,new Object[]{arg1,arg2});
}
protected static String format( String fmt, Object arg1, Object arg2, Object arg3 ) {
return MessageFormat.format(fmt,new Object[]{arg1,arg2,arg3});
}
protected static String format( String fmt, Object arg1, Object arg2, Object arg3, Object arg4 ) {
return MessageFormat.format(fmt,new Object[]{arg1,arg2,arg3,arg4});
}
}
msv-2009.1/tahiti/src/com/sun/tahiti/compiler/java/MarshallerSerializer.java 0000644 0001750 0001750 00000010606 07330362535 027271 0 ustar giovanni giovanni /*
* @(#)$Id: MarshallerSerializer.java 971 2001-07-27 22:04:13Z Bear $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.tahiti.compiler.java;
import com.sun.tahiti.util.xml.DOMVisitor;
import java.io.PrintWriter;
import java.util.Iterator;
import java.util.Map;
import java.util.StringTokenizer;
import org.w3c.dom.Element;
import org.w3c.dom.Document;
/**
* serializes simple marshaller to Java source code.
*
* @author
* Kohsuke KAWAGUCHI
*/
class MarshallerSerializer extends DOMVisitor {
/**
* produces the marshaller method.
*/
public static void write( Map fieldSerializers, PrintWriter out, Document dom ) {
out.println("\tpublic void marshall( Marshaller out ) {");
Iterator itr = fieldSerializers.values().iterator();
while( itr.hasNext() ) {
FieldSerializer fs = (FieldSerializer)itr.next();
String s = fs.marshallerInitializer();
if(s!=null)
out.println("\t\t"+s);
}
new MarshallerSerializer(fieldSerializers,out).visit(dom);
out.println("\t}");
out.println("");
}
private MarshallerSerializer( Map fieldSerializers, PrintWriter out ) {
this.fieldSerializers = fieldSerializers;
this.out = out;
}
/** a map from field name to FieldSerializer. */
private final Map fieldSerializers;
/** output will be sent to this object. */
private final PrintWriter out;
/**
* returns an Iterator that enumerates whitespace-delimited tokens in the
* given string.
*/
private Iterator tokinizeString( String s ) {
final StringTokenizer tokens = new StringTokenizer(s);
return new Iterator(){
public void remove() {
throw new UnsupportedOperationException();
}
public boolean hasNext() {
return tokens.hasMoreTokens();
}
public Object next() {
return tokens.nextToken();
}
};
}
/**
* constructs condition expression.
*/
private String getConditionExp( String exp ) {
Iterator itr = tokinizeString(exp);
boolean orNeeded = false;
StringBuffer buf = new StringBuffer();
while( itr.hasNext() ) {
if(orNeeded)
buf.append(" || ");
orNeeded = true;
buf.append( getSerializer((String)itr.next()).hasMoreToken() );
}
return buf.toString();
}
public void visit( Element e ) {
final String tagName = e.getTagName();
if(tagName.equals("group")) {
super.visit(e);
return;
}
if(tagName.equals("oneOrMore")) {
String exp = e.getAttribute("while");
println("do {");
indent++;
super.visit(e);
indent--;
println("} while( "+
getConditionExp(exp)+" );");
return;
}
if(tagName.equals("choice")) {
super.visit(e);
return;
}
if(tagName.equals("option")) {
String exp = e.getAttribute("if");
println("if( "+ getConditionExp(exp) +" ) {");
indent++;
super.visit(e);
indent--;
println("} else");
return;
}
if(tagName.equals("otherwise")) {
println("{");
indent++;
super.visit(e);
indent--;
println("}");
return;
}
if(tagName.equals("epsilon")) {
println(";");
return;
}
if(tagName.equals("notPossible")) {
println("// assertion failed.");
println("throw new Error();");
return;
}
if(tagName.equals("marshall")) {
String exp = e.getAttribute("fieldName");
println( getSerializer(exp).marshall(e) );
return;
}
if(tagName.equals("element") || tagName.equals("attribute")) {
String uri = e.getAttribute("uri");
String local = e.getAttribute("name");
String methodName = tagName.equals("element")?"Element":"Attribute";
println( "out.start"+methodName+"("+quote(uri)+","+quote(local)+");" );
super.visit(e);
println( "out.end"+methodName+"("+quote(uri)+","+quote(local)+");" );
return;
}
throw new Error("unknown tag name:"+tagName);
}
private static String quote( String body ) {
return "\""+body+"\"";
}
/** gets the FieldSerializer for the specified field. */
private FieldSerializer getSerializer( String fieldName ) {
FieldSerializer s = (FieldSerializer)fieldSerializers.get(fieldName);
if(s==null) // assertion
throw new Error(fieldName);
return s;
}
private int indent = 2;
/** print a string with indentation. */
private void println( String s) {
for( int i=0; iKohsuke KAWAGUCHI
*/
class VectorFieldSerializer extends FieldSerializer
{
VectorFieldSerializer( ClassSerializer parent, FieldUse fu ) {
super(parent,fu);
}
void writeVariableDef( PrintWriter out, AccessModifier mod ) {
out.println("\t"+mod+" "+getTypeStr()+" "+fu.name+
" = new "+getTypeStr()+"();");
}
void writeGetterDef( PrintWriter out, AccessModifier mod ) {
out.println(Formatter.format(
" <%0> int get<%1>Size() {\n"+
" return <%2>.size();\n"+
" }\n"+
" <%0> <%4> get<%1>( int idx ) {\n"+
" return (<%4>)<%2>.get(idx);\n"+
" }\n"+
" <%0> java.util.Iterator iterate<%1>() {\n"+
" return <%2>.iterator();\n"+
" }\n"+
" <%0> <%4>[] get<%1>s() {\n"+
" return (<%4>[])<%2>.toArray(new <%4>[<%2>.size()]);\n"+
" }\n",
new Object[]{
mod, capitalizedFieldName, fu.name, getTypeStr(),
parent.toPrintName(fu.type)
}));
}
void writeSetterDef( PrintWriter out, AccessModifier mod ) {
out.println(Formatter.format(
" <%0> void clear<%1>() {\n"+
" <%2>.clear();\n"+
" }\n"+
" <%0> <%4> set<%1>( int idx, <%4> item ) {\n"+
" return (<%4>)<%2>.set(idx,item);\n"+
" }\n"+
" <%0> void add<%1>( <%4> item ) {\n"+
" <%2>.add(item);\n"+
" }\n",
new Object[]{
mod, capitalizedFieldName, fu.name, getTypeStr(),
parent.toPrintName(fu.type)
}));
}
String getTypeStr() {
return "java.util.Vector /* of " + parent.toPrintName(fu.type) +" */";
}
String setField( String objName ) {
return format("this.{0}.add({1});",fu.name,objName);
}
String marshallerInitializer() {
return format("int idx_{0}=0; int len_{0}={0}.size();", fu.name );
}
String hasMoreToken() {
// TODO: this code becomes wrong if we allow primitive types
// as the type.
return format("idx_{0}!=len_{0}", fu.name );
}
String marshall( Element e ) {
if( fu.type instanceof ClassItem || fu.type instanceof InterfaceItem )
return format("(({0}){1}.get(idx_{1}++)).marshall(out);",
parent.toPrintName(fu.type), fu.name );
else
return format("out.data(({0}){1}.get(idx_{1}++), {2}.{3});",
parent.toPrintName(fu.type), fu.name,
parent.grammarShortClassName, e.getAttribute("dataSymbol") );
}
}
msv-2009.1/tahiti/src/com/sun/tahiti/compiler/java/SetFieldSerializer.java 0000644 0001750 0001750 00000005312 07337077746 026712 0 ustar giovanni giovanni /*
* @(#)$Id: SetFieldSerializer.java 1083 2001-08-17 02:22:30Z Bear $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.tahiti.compiler.java;
import com.sun.tahiti.grammar.*;
import com.sun.tahiti.util.text.Formatter;
import java.io.PrintWriter;
import org.w3c.dom.Element;
/**
* serializes a collection field by using a Set.
*
* @author
* Kohsuke KAWAGUCHI
*/
class SetFieldSerializer extends FieldSerializer
{
SetFieldSerializer( ClassSerializer parent, FieldUse fu ) {
super(parent,fu);
}
void writeVariableDef( PrintWriter out, AccessModifier mod ) {
out.println("\t"+mod+" "+getTypeStr()+" "+fu.name+
" = new "+getTypeStr()+"();");
}
void writeGetterDef( PrintWriter out, AccessModifier mod ) {
out.println(Formatter.format(
" <%0> int get<%1>Size() {\n"+
" return <%2>.size();\n"+
" }\n"+
" <%0> boolean contains<%1>( <%4> item ) {\n"+
" return <%2>.contains(item);\n"+
" }\n"+
" <%0> java.util.Iterator iterate<%1>() {\n"+
" return <%2>.iterator();\n"+
" }\n"+
" <%0> <%4>[] get<%1>s() {\n"+
" return (<%4>[])<%2>.toArray(new <%4>[<%2>.size()]);\n"+
" }\n",
new Object[]{
mod, capitalizedFieldName, fu.name, getTypeStr(),
parent.toPrintName(fu.type)
}));
}
void writeSetterDef( PrintWriter out, AccessModifier mod ) {
out.println(Formatter.format(
" <%0> void clear<%1>() {\n"+
" <%2>.clear();\n"+
" }\n"+
" <%0> boolean remove( <%4> item ) {\n"+
" return <%2>.remove(item);\n"+
" }\n"+
" <%0> boolean add<%1>( <%4> item ) {\n"+
" return <%2>.add(item);\n"+
" }\n",
new Object[]{
mod, capitalizedFieldName, fu.name, getTypeStr(),
parent.toPrintName(fu.type)
}));
}
String getTypeStr() {
return "java.util.Vector /* of " + parent.toPrintName(fu.type) +" */";
}
String setField( String objName ) {
return format("this.{0}.add({1});",fu.name,objName);
}
String marshallerInitializer() {
return format("int idx_{0}=0; int len_{0}={0}.size();", fu.name );
}
String hasMoreToken() {
// TODO: this code becomes wrong if we allow primitive types
// as the type.
return format("idx_{0}!=len_{0}", fu.name );
}
String marshall( Element e ) {
if( fu.type instanceof ClassItem || fu.type instanceof InterfaceItem )
return format("(({0}){1}.get(idx_{1}++)).marshall(out);",
parent.toPrintName(fu.type), fu.name );
else
return format("out.data(({0}){1}.get(idx_{1}++), {2}.{3});",
parent.toPrintName(fu.type), fu.name,
parent.grammarShortClassName, e.getAttribute("dataSymbol") );
}
}
msv-2009.1/tahiti/src/com/sun/tahiti/compiler/java/ClassSerializer.java 0000644 0001750 0001750 00000024722 07337343356 026257 0 ustar giovanni giovanni /*
* @(#)$Id: ClassSerializer.java 1087 2001-08-18 01:37:50Z Bear $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.tahiti.compiler.java;
import com.sun.msv.grammar.*;
import com.sun.tahiti.compiler.Symbolizer;
import com.sun.tahiti.compiler.Controller;
import com.sun.tahiti.compiler.XMLWriter;
import com.sun.tahiti.compiler.sm.MarshallerGenerator;
import com.sun.tahiti.grammar.*;
import com.sun.tahiti.grammar.util.Multiplicity;
import com.sun.tahiti.reader.NameUtil;
import com.sun.tahiti.util.text.Formatter;
import com.sun.tahiti.util.xml.XSLTUtil;
import com.sun.tahiti.util.xml.DOMVisitor;
import com.sun.tahiti.util.xml.DOMBuilder;
import java.io.IOException;
import java.io.OutputStream;
import java.io.PrintWriter;
import java.util.Iterator;
import java.util.Map;
import java.util.Vector;
import java.text.MessageFormat;
import org.w3c.dom.Element;
import org.xml.sax.SAXException;
/**
* produces Java source codes of the object model.
*
* @author
* Kohsuke KAWAGUCHI
*/
public class ClassSerializer
{
public ClassSerializer( AnnotatedGrammar grammar, Symbolizer symbolizer, Controller controller ) {
this.grammar = grammar;
this.symbolizer = symbolizer;
this.controller = controller;
this.grammarClassName = grammar.grammarName;
int idx = grammarClassName.lastIndexOf('.');
if(idx<0) grammarShortClassName = grammarClassName;
else grammarShortClassName = grammarClassName.substring(idx+1);
}
private final AnnotatedGrammar grammar;
private final Symbolizer symbolizer;
private final Controller controller;
/** fully-qualified name of the Gramamr class. */
protected final String grammarClassName;
/**
* bare class name of the Grammar class.
* Since the Grammar class is imported in generated classes,
* this bare name can be used to refer to the Grammar class.
*/
protected final String grammarShortClassName;
public void generate() throws IOException {
// collect all ClassItems.
ClassItem[] types = grammar.getClasses();
for( int i=0; ilist of derived types");
hasDerivedType |= listDerivedTypes(type,grammar.iterateClasses());
hasDerivedType |= listDerivedTypes(type,grammar.iterateInterfaces());
if(!hasDerivedType)
out.println(" * no derived type");
out.println(" */");
}
protected boolean listDerivedTypes( TypeItem current, Iterator itr ) {
boolean hasDerivedType = false;
while( itr.hasNext() ) {
TypeItem type = (TypeItem)itr.next();
boolean isDerived = false;
if(type.getSuperType()==current)
isDerived = true;
Type[] itfs = type.getInterfaces();
for( int i=0; i
* We use non-collection class (String,Float,MyXYZType) as
* the field type.
*
* @author
* Kohsuke KAWAGUCHI
*/
class AtmostOneFieldSerializer extends SingleFieldSerializer
{
AtmostOneFieldSerializer( ClassSerializer parent, FieldUse fu ) {
super(parent,fu);
}
String getTypeStr() {
return parent.toPrintName(fu.type);
}
String setField( String objName ) {
return format("this.{0}=({1}){2};",fu.name,getTypeStr(),objName);
}
String hasMoreToken() {
return format("{0}!=null", fu.name );
}
String marshall( Element e ) {
if( fu.type instanceof ClassItem || fu.type instanceof InterfaceItem )
return format("{0}.marshall(out);", fu.name );
else
return format("out.data({0},{1}.{2});", fu.name,
parent.grammarShortClassName, e.getAttribute("dataSymbol") );
}
String marshallerInitializer() {
return null;
}
}
msv-2009.1/tahiti/src/com/sun/tahiti/compiler/java/PrimitiveTypeFieldSerializer.java 0000644 0001750 0001750 00000003425 07337072463 030763 0 ustar giovanni giovanni /*
* @(#)$Id: PrimitiveTypeFieldSerializer.java 1081 2001-08-17 01:36:51Z Bear $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.tahiti.compiler.java;
import com.sun.tahiti.grammar.*;
import java.io.PrintWriter;
import org.w3c.dom.Element;
/**
* serializes a field of Java built-in type with (1,1) multiplicity.
*
*
* (1,1) multiplicity implies that the field is always present.
* Therefore the field never need to be null (, which indicates
* that the value is absent).
*
*
* In this case and in this case only,
* Java built-in types (int,float, etc.) can be used directly as the field type.
*
* @author
* Kohsuke KAWAGUCHI
*/
class PrimitiveTypeFieldSerializer extends SingleFieldSerializer {
public PrimitiveTypeFieldSerializer( ClassSerializer parent, FieldUse fu ) {
super(parent,fu);
boxType = parent.toPrintName(fu.type);
primitiveType = (String)boxTypes.get(fu.type.getTypeName());
}
/**
* name of the "box" type. Things like "Integer","Float",...
*/
private final String boxType;
/**
* name of the primitive type. Things like "int","float", ...
*/
private final String primitiveType;
String getTypeStr() {
return primitiveType;
}
String setField( String objName ) {
return format("this.{0}=(({1}){2}).{3}Value();",
fu.name, boxType, objName, primitiveType );
}
String marshallerInitializer() {
return null;
}
String hasMoreToken() {
return "true";
}
String marshall( Element e ) {
return format("out.data(new {0}({1}),{2}.{3});",
boxType, fu.name,
parent.grammarShortClassName, e.getAttribute("dataSymbol") );
}
}
msv-2009.1/tahiti/src/com/sun/tahiti/compiler/java/SingleFieldSerializer.java 0000644 0001750 0001750 00000001536 07337072463 027373 0 ustar giovanni giovanni package com.sun.tahiti.compiler.java;
import com.sun.tahiti.grammar.*;
import java.io.PrintWriter;
abstract class SingleFieldSerializer extends FieldSerializer
{
public SingleFieldSerializer( ClassSerializer parent, FieldUse fu ) {
super(parent,fu);
}
void writeVariableDef( PrintWriter out, AccessModifier mod ) {
out.println("\t"+mod+" "+getTypeStr()+" "+fu.name+";");
}
void writeGetterDef( PrintWriter out, AccessModifier mod ) {
out.println("\t"+mod+" "+getTypeStr()+" get"+capitalizedFieldName+"() {");
out.println("\t\treturn this."+fu.name+";");
out.println("\t}");
out.println();
}
void writeSetterDef( PrintWriter out, AccessModifier mod ) {
out.println("\t"+mod+" void set"+capitalizedFieldName+"( "+getTypeStr()+" newVal ) {");
out.println("\t\tthis."+fu.name+" = newVal;");
out.println("\t}");
out.println();
}
}
msv-2009.1/tahiti/src/com/sun/tahiti/compiler/ControllerImpl.java 0000644 0001750 0001750 00000002261 07326114117 025163 0 ustar giovanni giovanni /*
* @(#)$Id: ControllerImpl.java 923 2001-07-20 20:45:03Z Bear $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.tahiti.compiler;
import com.sun.msv.reader.GrammarReaderController;
import org.xml.sax.Locator;
import org.xml.sax.InputSource;
import org.xml.sax.SAXException;
import java.io.IOException;
/**
* an implementation of the Controller interface.
*
* This implementation delegates GrammarReaderController events to
* another object.
*
* @author
* Kohsuke KAWAGUCHI
*/
public abstract class ControllerImpl implements Controller {
protected ControllerImpl( GrammarReaderController core ) {
this.core = core;
}
protected GrammarReaderController core;
public void error( Locator[] locs, String msg, Exception e ) {
core.error( locs, msg, e );
}
public void warning( Locator[] locs, String msg ) {
core.warning( locs, msg );
}
public InputSource resolveEntity( String a, String b )
throws SAXException, IOException {
return core.resolveEntity(a,b);
}
}
msv-2009.1/tahiti/src/com/sun/tahiti/compiler/ll/ 0000755 0001750 0001750 00000000000 11622453065 021763 5 ustar giovanni giovanni msv-2009.1/tahiti/src/com/sun/tahiti/compiler/ll/ParserTable.java 0000644 0001750 0001750 00000006351 07337343356 025050 0 ustar giovanni giovanni /*
* @(#)$Id: ParserTable.java 1087 2001-08-18 01:37:50Z Bear $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.tahiti.compiler.ll;
import java.util.Set;
import java.util.HashSet;
import java.util.Map;
import java.util.HashMap;
import java.util.Iterator;
import com.sun.msv.grammar.Expression;
import com.sun.tahiti.compiler.XMLWriter;
import com.sun.tahiti.compiler.Symbolizer;
/**
* parser table.
*
* A parser table is conceptually a two dimensional array, whose cell is a
* set of Rule objects.
*
* @author
* Kohsuke KAWAGUCHI
*/
public class ParserTable
{
/**
* actual storage.
* type: Non-terminal -> ( terminal -> set(Rule) )
*/
private final Map impl = new HashMap();
/** add a new rule. */
public void addRule( Expression nonTerminal, Expression terminal, Rule rule ) {
Set s = getOrCreateRuleSet(nonTerminal,terminal);
s.add(rule);
}
/** add a new rule. */
public void addRules( Expression nonTerminal, Set terminals, Rule rule ) {
// TODO: could be better implemented
Iterator itr = terminals.iterator();
while( itr.hasNext() )
getOrCreateRuleSet( nonTerminal, (Expression)itr.next() ).add(rule);
}
private Set getOrCreateRuleSet( Expression nonTerminal, Expression terminal ) {
Map m = (Map)impl.get(nonTerminal);
if(m==null)
impl.put(nonTerminal,m=new HashMap());
Set s = (Set)m.get(terminal);
if(s==null)
m.put(terminal,s=new HashSet());
return s;
}
/**
* writes the contents of the table as XML.
*/
public void write( XMLWriter writer, Symbolizer symbolizer ) {
writer.start("parserTable");
int no = 0;
Iterator itr = impl.keySet().iterator();
while( itr.hasNext() ) {
Expression nonTerm = (Expression)itr.next();
Map t2r = (Map)impl.get(nonTerm);
writer.start("action",
new String[]{"stackTop",symbolizer.getId(nonTerm)});
Rule defaultAction=null;
{
Set defaultActionSet = (Set)t2r.get(Expression.epsilon);
if(defaultActionSet!=null) {
if(defaultActionSet.size()>1)
// only one default action is possible
throw new Error();
if(defaultActionSet.size()==1)
defaultAction = (Rule)defaultActionSet.toArray()[0];
}
}
Iterator jtr = t2r.keySet().iterator();
while( jtr.hasNext() ) {
Expression term = (Expression)jtr.next();
// applicable rules.
Rule[] rules = (Rule[])((Set)t2r.get(term)).toArray(new Rule[0]);
if( rules.length==1 && rules[0]==defaultAction && term!=Expression.epsilon )
continue; // this token statement can be absorbed by the "otherwise" clause.
if( term!=Expression.epsilon )
writer.start( "token",
new String[]{
"id", symbolizer.getId(term),
"no", Integer.toString(no++)});
else
writer.start( "otherwise" );
for( int i=0; iKohsuke KAWAGUCHI
*/
public final class Rule {
/**
* right-hand side of the rules.
*
* Expression.epsilon is used to denote A -> $epsilon.
* TypedStringExp is used instead of Datatype.
*/
public Expression[] right;
public boolean isInterleave;
public Rule( Expression[] right, boolean isInterleave ) {
this.right = right;
this.isInterleave = isInterleave;
assert(right!=null);
for( int i=0; i B), then we can change the interleaveness of the rule.
if(replace.right.length==1)
interleave = this.isInterleave;
else
if(this.right.length==1)
interleave = replace.isInterleave;
else
if(this.isInterleave!=replace.isInterleave)
// if one is an interleaving rule and the other is a normal rule,
// then we can't rewrite rules.
return false;
else
interleave = this.isInterleave;
int rlen = replace.right.length;
if(rlen==1 && replace.right[0]==Expression.epsilon)
rlen=0; // coerce epsilon
Expression[] seq = new Expression[right.length+rlen-1];
if(seq.length==0)
seq = new Expression[]{Expression.epsilon};
else {
System.arraycopy( right, 0, seq, 0, idx );
System.arraycopy( replace.right, 0, seq, idx, rlen );
System.arraycopy( right, idx+1, seq, idx+rlen, right.length-(idx+1) );
}
this.right = seq;
this.isInterleave = interleave;
return true;
}
/**
* produces the string representation of this rule.
* Mainly for debugging.
*/
public String toString( Symbolizer symbolizr ) {
StringBuffer buf = new StringBuffer();
buf.append( " --> ");
if(isInterleave)
buf.append("(interleave) ");
for( int i=0; i, we have to spit the filter definition.
// But we don't need a filter for the first one symbol.
writer.start("filter");
Iterator itr = FilterCalculator.calc(right[i]).iterator();
while(itr.hasNext())
writer.element("item",new String[]{"symbolRef",symbolizer.getId(itr.next())});
writer.end("filter");
}
writer.end("item");
}
writer.end("right");
writer.end("rule");
}
private static void assert( boolean b ) {
if(!b) throw new Error();
}
}
msv-2009.1/tahiti/src/com/sun/tahiti/compiler/ll/LLTableCalculator.java 0000644 0001750 0001750 00000010674 07365333167 026140 0 ustar giovanni giovanni /*
* @(#)$Id: LLTableCalculator.java 1256 2001-10-23 18:27:03Z Bear $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.tahiti.compiler.ll;
import com.sun.msv.grammar.*;
import com.sun.tahiti.compiler.Symbolizer;
import java.util.Map;
import java.util.Iterator;
import java.util.Set;
/**
* computes LL parser table from annotated AGM.
*
* @author
* Kohsuke KAWAGUCHI
*/
public class LLTableCalculator
{
// private use only. call the calc method.
private LLTableCalculator() {}
private Rules rules;
// actual type: Non-terminal -> ( terminal -> set(Rule) )
final ParserTable table = new ParserTable();
/**
* @param allRules
* all rules in this grammar.
* @param startSymbol
* ElementExp or AttributeExp which is used as the start symbol.
*/
public static ParserTable calc( Expression startSymbol, Rules allRules, ExpressionPool pool, Symbolizer symbolizer ) {
return new LLTableCalculator()._calc(startSymbol,allRules,pool,symbolizer);
}
private ParserTable _calc( Expression startSymbol, Rules allRules, final ExpressionPool pool, Symbolizer symbolizer ) {
/*
Step.1
======
compute all rules reachable from the current start symbol,
and store them into the "rules" field.
*/
rules = allRules.removeUnreachableRules(startSymbol,false);
/*
Step.3
======
compute ParserTable[A,a] and store them into the "parserTable" field.
*/
// for each "X->rule"...
for( Iterator itr=rules.iterateKeys(); itr.hasNext(); ) {
final Expression nonTerminal = (Expression)itr.next();
Rule[] rs = rules.getAll(nonTerminal);
if( rs.length==1 ) {
// if there is only one rule to expand, the only possible action is
// to expand it (no matter what the input token is.
table.addRule( nonTerminal, Expression.epsilon, rs[0] );
} else {
for( int i=0; i should have been removed already.
throw new Error();
}
public void onConcur( ConcurExp exp ) {
// not supported
throw new Error();
}
public void onAttribute( AttributeExp exp ) {
r.add(exp);
}
public void onElement( ElementExp exp ) {
r.add(exp);
}
public void onAnyString() {
r.add( Expression.anyString );
}
});
return r;
}
private static void assert( boolean b ) {
if(!b) throw new Error();
}
}
msv-2009.1/tahiti/src/com/sun/tahiti/compiler/ll/FilterCalculator.java 0000644 0001750 0001750 00000002667 07326114117 026076 0 ustar giovanni giovanni /*
* @(#)$Id: FilterCalculator.java 923 2001-07-20 20:45:03Z Bear $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.tahiti.compiler.ll;
import com.sun.msv.grammar.*;
import com.sun.msv.grammar.util.ExpressionWalker;
import java.util.Set;
/**
* computes the filter that will be used to parse <interleave>.
*
*
* See the document of LL marshaller for why such a filter is necessary.
*
*
* This class traverses the child elements and creates a name class that
* contains all possible element names.
*
* @author
* Kohsuke KAWAGUCHI
*/
public class FilterCalculator {
// use the calc method.
private FilterCalculator() {}
/**
* computes the set of all element symbols in this branch.
*/
public static Set calc( Expression exp ) {
// compute the possible names.
ElementNameCollector col = new ElementNameCollector();
exp.visit(col);
// simplify it
return col.symbols;
}
private static class ElementNameCollector extends ExpressionWalker {
Set symbols = new java.util.HashSet();
public void onElement( ElementExp exp ) {
symbols.add(exp);
// don't visit the content model.
}
public void onAttribute( AttributeExp exp ) {
// we don't need to traverse the body of attribute.
}
}
}
msv-2009.1/tahiti/src/com/sun/tahiti/compiler/ll/RuleGenerator.java 0000644 0001750 0001750 00000030254 07365333167 025421 0 ustar giovanni giovanni /*
* @(#)$Id: RuleGenerator.java 1256 2001-10-23 18:27:03Z Bear $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.tahiti.compiler.ll;
import com.sun.msv.grammar.*;
import com.sun.tahiti.grammar.*;
import java.util.Map;
import java.util.Set;
import java.util.Vector;
import java.util.Iterator;
/**
* creates raw production rules for a grammar.
*
* @author
* Kohsuke KAWAGUCHI
*/
public class RuleGenerator
{
private static java.io.PrintStream debug = null;
/**
* creates production rules.
*
* @return
* a map from Expressions (as non-terminal symbols) to
* Rule[] (possible expansion rules).
*
*
* Note that if
* map.get(x)=={r1,r2,...} then
* r1.left==r2.left==x.
*/
public static Rules create( Grammar g ) {
return new RuleGenerator()._create(g);
}
private RuleGenerator() {}
/**
* the production rules.
*/
private Rules rules = new Rules();
/**
* pool object that can be used to create Expressions during this process.
*/
private ExpressionPool pool;
/** grammar object that we are dealing with. */
private Grammar g;
private Rules _create( Grammar g ) {
pool = g.getPool();
this.g = g;
g.getTopLevel().visit( new ExpressionVisitorVoid(){
public void onElement( ElementExp exp ) {
if(visit(exp)) {
rules.add( exp, exp.contentModel );
exp.contentModel.visit(this);
}
}
public void onAttribute( AttributeExp exp ) {
if(visit(exp)) {
rules.add( exp, exp.exp );
exp.exp.visit(this);
}
}
public void onMixed( MixedExp exp ) {
throw new Error();
// treat this as
// p
}
public void onChoice( ChoiceExp exp ) {
if(visit(exp)) {
/*
Large choices are very common in many grammars.
Say we have a content model of A|B|C|D.
This content model is internally held as (A|(B|(C|D))),
which is binarized.
So the following casual rule expansion:
----------------------------------
rules.put( exp, new Rule[]{
new Rule( exp, new Expression[]{exp.exp1} ),
new Rule( exp, new Expression[]{exp.exp2} ) } );
exp.exp1.visit(this);
exp.exp2.visit(this);
----------------------------------
will result in the following redundant rules:
A|B|C|D -> A
A|B|C|D -> B|C|D
B|C|D -> B
B|C|D -> C|D
C|D -> C
C|D -> D
Instead, we'd like to have the following rules.
A|B|C|D -> A
A|B|C|D -> B
A|B|C|D -> C
A|B|C|D -> D
To do this, we are scanning all branches of choice at once.
Note that the modified rules look concise, but actually
it is not always a good choice.
*/
rules.add( exp, exp.exp1 );
rules.add( exp, exp.exp2 );
exp.exp1.visit(this);
exp.exp2.visit(this);
}
}
public void onConcur( ConcurExp exp ) {
// not supported.
throw new Error();
}
public void onSequence( SequenceExp exp ) {
if(visit(exp)) {
rules.add( exp, new Expression[]{exp.exp1,exp.exp2}, false );
exp.exp1.visit(this);
exp.exp2.visit(this);
}
}
public void onInterleave( InterleaveExp exp ){
if(visit(exp)) {
// add interleave rule.
rules.add( exp, new Expression[]{exp.exp1,exp.exp2}, true );
exp.exp1.visit(this);
exp.exp2.visit(this);
}
}
public void onNullSet() {
// nullSet must be removed before this process.
throw new Error();
}
public void onEpsilon() {
// there is no rule associated with the epsilon
// this is a terminal symbol.
}
public void onList( ListExp exp ) {
if(visit(exp)) {
rules.add( exp, exp.exp );
exp.exp.visit(this);
}
}
// these are terminal symbols
public void onData( DataExp exp ) {}
public void onValue( ValueExp exp ) {}
public void onAnyString() {}
public void onOneOrMore( OneOrMoreExp exp ) {
if(visit(exp)) {
Expression item = exp.exp;
Expression intermediate = pool.createZeroOrMore(item);
if( intermediate==exp ) {
// if item is epsilon-reducible, then createZeroOrMore returns
// the same expression as exp. This case has to be treated
// differently.
rules.add( exp, Expression.epsilon );
rules.add( exp, new Expression[]{item,intermediate}, false );
} else {
rules.add( exp, new Expression[]{item,intermediate}, false );
}
item.visit(this);
// this will create rules for the "intermediate"
intermediate.visit(this);
}
}
public void onRef( ReferenceExp exp ) {
if(visit(exp)) {
rules.add( exp, exp.exp );
exp.exp.visit(this);
}
}
public void onOther( OtherExp exp ) {
if(visit(exp)) {
rules.add( exp, exp.exp );
exp.exp.visit(this);
}
}
/**
* this method returns true if the specified expression
* is not visited before.
*
* Care has to be taken not to traverse children before
* adding production rules for the parent, because this method
* assumes that visited expressions have associated production rules.
*/
private boolean visit( Expression exp ) {
return !rules.contains(exp);
}
});
/*
perform a little optimization.
If there is a rule A := xyz (or x&y&z) that satisfies
the following properties,
then we can rewrite the occurence of A by xyz (with
a restriction concerning the interleave property).
1. A := xyz is the only rule which has A as the left hand side.
2. A does not have associated action.
That is, nothing is executed when A is expanded to B (or B is
reduced to A).
3. A is not Element/Attribute. (these rules are significant and
therefore cannot be removed.)
*/
// a map from Expression to Expression[]
Map redundantSymbols = new java.util.HashMap();
for( Iterator itr=rules.iterateKeys(); itr.hasNext(); ) {
final Expression left = (Expression)itr.next();
final Rule[] rs = rules.getAll(left);
// if this rule is in the form of "A:=xyz" and this is the only rule
// which has A as the left hand side,
if( rs.length==1 ) {
// if this rule does not have associated action.
if( isActionlessNonTerminal(left)
// and A is a pure non-terminal
&& !(left instanceof NameClassAndExpression) ) {
redundantSymbols.put( left, rs[0] );
}
}
}
// rewrite rules
rewriteRules( redundantSymbols );
// clean-up.
rules = rules.removeUnreachableRules(g.getTopLevel(),true);
/*
perform another optimization.
If there is a rule A := xyz (or x&y&z) that satisfies
the following properties,
then we can rewrite the occurence of A by xyz (with
a restriction concerning the interleave property).
1. A is used only once, and its occurence must be the left most.
That is, there must be a rule X->Abcd... and this is the only
occasion of A in the entire rules.
The reason of this restriction is the ambiguity. If the
rules are X->stA, A->b, and A->c and if we expand this A, the result
will be X->stb and X->stc, which is ambiguous.
2. A does not have associated action.
That is, nothing is executed when A is expanded to B (or B is
reduced to A).
3. A is not Element/Attribute. (these rules are significant and
therefore cannot be removed.)
*/
{
Set occuredSymbols = new java.util.HashSet();
Set candidates = new java.util.HashSet();
for( Iterator itr=rules.iterateKeys(); itr.hasNext(); ) {
final Expression left = (Expression)itr.next();
Rule[] rs = rules.getAll(left);
for( int i=0; i X".
I'm not exactly sure if this is the right solution to the problem,
but these production rules can be produced from the following pattern:
(X)
(Y)
A
raw rules:
X -> Y X
X -> \epsilon
Y -> \epsilon
Y -> A
By the optimization, Y is absorbed
X -> X
X -> A X
X -> \epsilon
*/
{
Iterator nonTerms = rules.iterateKeys();
while( nonTerms.hasNext() ) {
Expression left = (Expression)nonTerms.next();
Iterator/* of Rule*/ jtr = rules.get(left).iterator();
while( jtr.hasNext() ) {
final Rule r = (Rule)jtr.next();
if( r.right.length==1 && r.right[0]==left ) {
// this rule is the form of "X->X"
if(debug!=null)
debug.println("removing self-recursive rule");
jtr.remove();
}
}
}
}
rules.intern();
return rules;
}
/**
* rewrite the entire rules by replacing redundant symbols by
* their definitions, as specified by the map.
*
* @param redundantSymbols
* a map from symbols to its definitions. Occurences of these symbols
* in rules are replaced by its definitions.
*/
private void rewriteRules( Map redundantSymbols ) {
for( Iterator itr=rules.iterateKeys(); itr.hasNext(); ) {
final Expression symbol = (Expression)itr.next();
final Rule[] rs = rules.getAll(symbol);
for( int i=0; iKohsuke KAWAGUCHI
*/
public final class Rules {
/**
* set of all distinctive rules.
* This map can possibly contain unreachable object.
*/
private final Map distinctiveRules = new java.util.HashMap();
/**
* a map from left side symbol (Object) to the set of Rules.
*/
private final Map rules = new java.util.HashMap();
/** gets a Set that stores the values associated with the specified key. */
public Set get( Expression symbol ) {
Set s = (Set)rules.get(symbol);
if(s==null)
rules.put(symbol,s=new java.util.HashSet());
return s;
}
/** gets all values associated with the specified symbol. */
public Rule[] getAll( Expression symbol ) {
return (Rule[])get(symbol).toArray(new Rule[0]);
}
/** returns true if this container has a rule that expands the specified symbol
*/
public boolean contains( Expression symbol ) {
Set s = (Set)rules.get(symbol);
if(s==null) return false;
return s.size()!=0;
}
/** iterates non-terminal symbols in this rules. */
public Iterator iterateKeys() {
return rules.keySet().iterator();
}
Rule unifyRule( Rule r ) {
Rule unified = (Rule)distinctiveRules.get(r);
if(unified==null)
distinctiveRules.put( unified=r, r );
return unified;
}
/** adds a new rule. */
public void add( Expression left, Rule right ) {
get(left).add(unifyRule(right));
}
/** adds a new rule. */
public void add( Expression left, Expression[] right, boolean isInterleave ) {
add(left, new Rule(right,isInterleave));
}
/** adds a new rule. */
public void add( Expression left, Expression right ) {
add(left, new Expression[]{right}, false );
}
/** adds all rules. */
public void addAll( Expression left, Rule[] rules ) {
for( int i=0; i
* A rule which is unreachable from the specified rootSymbol
* will be removed.
*
* @param recurseElement
*
* if true, this method recursively visits element and attribute and
* discover all reachable rules. This is useful for global optimization.
*
*
* if set to false, this method treats element and attribute as terminal
* symbols. This is useful to extract per-element/per-attribute rules.
*/
public Rules removeUnreachableRules( Expression rootSymbol, boolean recurseElement ) {
Rules result = new Rules();
Set workQueue = new java.util.HashSet();
workQueue.add(rootSymbol);
while(!workQueue.isEmpty()) {
// get the first one in the queue.
Expression symbol = (Expression)workQueue.iterator().next();
workQueue.remove(symbol);
Rule[] rs = this.getAll(symbol);
assert(rs!=null && rs.length!=0);
result.addAll(symbol,rs);
for( int i=0; iKohsuke KAWAGUCHI
*/
class ExpressionSerializer {
/**
* this map will receive the order of serialization.
* expressions with the younger numbers should be serialized before
* the expressions with the older numbers.
*/
public final Map expr2id = new java.util.HashMap();
/**
* this set will receive the shared expressions.
*/
public final Set sharedExps = new java.util.HashSet();
/**
* generated XML representation should be sent to this object.
*/
public final XMLWriter out;
/**
* this object is used to resolve the symbol to its name.
*/
public final Symbolizer symbolizer;
ExpressionSerializer( Symbolizer symbolizer, XMLWriter out ) {
this.symbolizer = symbolizer;
this.out = out;
}
/** This visitor assigns serialization numbers to each expression. */
public final ExpressionVisitorVoid sequencer = new ExpressionVisitorVoid() {
/*
elements and attributes are not considered as particles.
their instances are created before anything else,
so we don't need to track dependency between them.
*/
public void onElement( ElementExp exp ) { return; }
public void onAttribute( AttributeExp exp ) { onExpr(exp); }
// not supported
public void onConcur( ConcurExp exp ) { throw new Error(); }
// never be possible. because is removed.
public void onNullSet() { throw new Error(); }
public void onData( DataExp exp ) {
if(onExpr(exp)) assignId(exp);
}
public void onValue( ValueExp exp ) {
if(onExpr(exp)) assignId(exp);
}
public void onMixed( MixedExp exp ) {
if(onExpr(exp)) {
exp.exp.visit(this);
assignId(exp);
}
}
public void onList( ListExp exp ) {
if(onExpr(exp)) {
exp.exp.visit(this);
assignId(exp);
}
}
public void onOneOrMore( OneOrMoreExp exp ) {
if(onExpr(exp)) {
exp.exp.visit(this);
assignId(exp);
}
}
// TODO: ReferenceExps/OtherExps are unnecessary.
// we should be able to ignore them.
public void onRef( ReferenceExp exp ) {
if(onExpr(exp)) {
exp.exp.visit(this);
assignId(exp);
}
}
public void onOther( OtherExp exp ) {
if(onExpr(exp)) {
exp.exp.visit(this);
assignId(exp);
}
}
// epsilon is always available through Expression.epsilon,
// so we don't need to compute dependency.
public void onEpsilon() { return; }
public void onAnyString() { return; }
public void onSequence( SequenceExp exp ) { onBinExp(exp); }
public void onChoice( ChoiceExp exp ) { onBinExp(exp); }
public void onInterleave( InterleaveExp exp){ onBinExp(exp); }
private void onBinExp( BinaryExp exp ) {
if(onExpr(exp)) {
exp.exp1.visit(this);
exp.exp2.visit(this);
assignId(exp);
}
}
/**
* this method is called for every particles.
*
* @return true
* if the caller should traverse its descendants.
*/
private boolean onExpr( Expression exp ) {
if( expr2id.containsKey(exp) ) {
// this expression is already visited.
sharedExps.add( exp );
// since this expression is already visited,
// there is no need to traverse its children.
return false;
} else {
// this is the first time to visit this expression.
// let the caller traverse the children.
return true;
// we will number this expression in post-order fashion.
}
}
};
/**
* assigns an unique ID for an expression.
*/
public void assignId( Expression exp ) {
if( expr2id.containsKey(exp) ) throw new Error("assertion failed");
expr2id.put( exp, new Integer(expr2id.size()) );
}
/** then this visitor will serialize them into Java source code.
*/
public final ExpressionVisitorVoid serializer = new ExpressionVisitorVoid() {
public void onElement( ElementExp exp ) {
serialize(exp.contentModel);
}
public void onAttribute( AttributeExp exp ) {
serialize(exp.exp);
}
// not supported
public void onConcur( ConcurExp exp ) { throw new Error(); }
// never be possible. because is removed.
public void onNullSet() { throw new Error(); }
public void onData( DataExp exp ) {
out.element("typedString",
new String[]{"dataSymbolRef",symbolizer.getId(exp)});
}
public void onValue( ValueExp exp ) {
out.element("typedString",
new String[]{"dataSymbolRef",symbolizer.getId(exp)});
}
public void onMixed( MixedExp exp ) {
out.start("mixed");
serialize(exp.exp);
out.end("mixed");
}
public void onList( ListExp exp ) {
out.start("list");
serialize(exp.exp);
out.end("list");
}
public void onOneOrMore( OneOrMoreExp exp ) {
out.start("oneOrMore");
serialize(exp.exp);
out.end("oneOrMore");
}
public void onRef( ReferenceExp exp ) {
serialize(exp.exp);
}
public void onOther( OtherExp exp ) {
serialize(exp.exp);
}
public void onEpsilon() {
out.element("epsilon");
}
public void onAnyString() {
out.element("text");
}
public void onSequence( SequenceExp exp ) { onBinExp("group",exp); }
public void onChoice( ChoiceExp exp ) { onBinExp("choice",exp); }
public void onInterleave( InterleaveExp exp) { onBinExp("interleave",exp); }
private void onBinExp( String name, BinaryExp exp ) {
out.start(name);
serialize(exp.exp1);
serialize(exp.exp2);
out.end(name);
}
};
/**
* serializes an Expression. If the specified "exp" is shared,
* this method writes a reference.
*/
public void serialize( Expression exp ) {
if(exp instanceof ElementExp) {
out.element("element",
new String[]{"symbolRef",symbolizer.getId(exp)});
} else
if(exp instanceof AttributeExp) {
out.element("attribute",
new String[]{"symbolRef",symbolizer.getId(exp)});
} else
if(sharedExps.contains(exp)) {
// if this expression is shared, spit the reference.
out.element("ref",
new String[]{"particle","o"+((Integer)expr2id.get(exp)).toString()});
} else {
// otherwise perform recursion.
exp.visit(serializer);
}
}
/**
* generates canonical XML representation of the name class.
*/
public static void serializeNameClass( NameClass nc, final XMLWriter out ) {
out.start("name");
nc.visit( new NameClassVisitor(){
public Object onChoice( ChoiceNameClass nc ) {
out.start("choice");
nc.nc1.visit(this);
nc.nc2.visit(this);
out.end("choice");
return null;
}
public Object onAnyName( AnyNameClass nc ) {
out.element("anyName");
return null;
}
public Object onNsName( NamespaceNameClass nc ) {
out.element("nsName",new String[]{"ns",nc.namespaceURI});
return null;
}
public Object onNot( NotNameClass nc ) {
out.start("not");
nc.child.visit(this);
out.end("not");
return null;
}
public Object onDifference(DifferenceNameClass nc) {
out.start("difference");
nc.nc1.visit(this);
nc.nc2.visit(this);
out.end("difference");
return null;
}
public Object onSimple(SimpleNameClass nc) {
out.element("name",
new String[]{"ns",nc.namespaceURI,"local",nc.localName});
return null;
}
});
out.end("name");
}
}
msv-2009.1/tahiti/src/com/sun/tahiti/compiler/ll/Util.java 0000644 0001750 0001750 00000001161 07365333167 023553 0 ustar giovanni giovanni /*
* @(#)$Id: Util.java 1256 2001-10-23 18:27:03Z Bear $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.tahiti.compiler.ll;
import com.sun.msv.grammar.*;
/**
* LL grammar related utility methods.
*
* @author
* Kohsuke KAWAGUCHI
*/
class Util
{
public static boolean isTerminalSymbol( Expression exp ) {
return exp instanceof DataOrValueExp
|| exp==Expression.anyString
|| exp==Expression.epsilon;
}
}
msv-2009.1/tahiti/src/com/sun/tahiti/compiler/ll/RuleSerializer.java 0000644 0001750 0001750 00000035505 07365333167 025610 0 ustar giovanni giovanni /*
* @(#)$Id: RuleSerializer.java 1256 2001-10-23 18:27:03Z Bear $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.tahiti.compiler.ll;
import com.sun.msv.datatype.xsd.XSDatatype;
import com.sun.msv.grammar.*;
import com.sun.msv.grammar.util.ExpressionWalker;
import com.sun.tahiti.compiler.XMLWriter;
import com.sun.tahiti.compiler.Symbolizer;
import com.sun.tahiti.grammar.*;
import com.sun.tahiti.reader.TypeUtil;
import com.sun.tahiti.reader.NameUtil;
import org.relaxng.datatype.Datatype;
import org.xml.sax.DocumentHandler;
import org.xml.sax.SAXException;
import java.io.PrintStream;
import java.util.Map;
import java.util.Set;
import java.util.Iterator;
import java.text.MessageFormat;
/**
* serializes a LL grammar into the XML representation.
*
* @author
* Kohsuke KAWAGUCHI
*/
public class RuleSerializer implements Symbolizer {
private RuleSerializer() {}
/**
*
* @param grammar
* Grammar object to be generated as a Java source code.
* @param rules
* production rules of the grammar. Actual type must be
* non-terminal -> Rule[].
* @param grammarClassName
* the fully-qualified name of the class that is going to be generated.
* @param outHandler
* Generated source code will be sent to this handler.
*
* @return
* return a symbolizer that is necessary to serialize class definitions.
*/
public static Symbolizer serialize( AnnotatedGrammar grammar, Rules rules, DocumentHandler outHandler ) throws SAXException {
RuleSerializer gen = new RuleSerializer();
gen._serialize( grammar, rules, outHandler );
return gen;
}
/**
* this map serves as a dictionary to lookup the name of the given symbol.
*/
final Map allNames = new java.util.HashMap();
public String getId( Object symbol ) {
if(symbol==null) return "null";
String s = (String)allNames.get(symbol);
if(s==null) {
System.out.println(symbol);
assert(false);
}
return s;
}
private void _serialize( AnnotatedGrammar grammar, Rules rules, DocumentHandler outHandler ) throws SAXException {
// add pre-defined special symbols.
allNames.put( Expression.epsilon, "epsilon" );
try {
final XMLWriter out = new XMLWriter(outHandler);
outHandler.setDocumentLocator(new org.xml.sax.helpers.LocatorImpl());
outHandler.startDocument();
outHandler.processingInstruction("xml-stylesheet","type='text/xsl' href='../grammarDebug.xslt'");
out.start("grammar");
{
int idx = grammar.grammarName.lastIndexOf('.');
if(idx<0) {
out.element("name", grammar.grammarName);
} else {
out.element("package", grammar.grammarName.substring(0,idx));
out.element("name", grammar.grammarName.substring(idx+1));
}
}
// collect various primitives (a map to its name)
//====================================================================
final Map elements = new java.util.HashMap(); // ElementExps
final Map attributes = new java.util.HashMap(); // AttributeExps
final Map datatypes = new java.util.HashMap(); // Datatypes
final Map classes = new java.util.HashMap(); // ClassItems
final Map fields = new java.util.HashMap(); // FieldItems
final Map primitives = new java.util.HashMap(); // PrimitiveItems
final Map ignores = new java.util.HashMap(); // IgnoreItems
grammar.getTopLevel().visit( new ExpressionWalker(){
public void onElement( ElementExp exp ) {
if(!elements.containsKey(exp)) {
elements.put(exp,computeName(exp.getNameClass(),elements));
super.onElement(exp);
}
}
public void onAttribute( AttributeExp exp ) {
if(!attributes.containsKey(exp)) {
attributes.put(exp,computeName(exp.nameClass,attributes));
super.onAttribute(exp);
}
}
public void onData( DataExp exp ) {
if(!datatypes.containsKey(exp)) {
datatypes.put(exp,computeName(exp.dt,datatypes));
super.onData(exp);
}
}
public void onValue( ValueExp exp ) {
if(!datatypes.containsKey(exp)) {
datatypes.put(exp,computeName(exp.dt,datatypes));
super.onValue(exp);
}
}
public void onOther( OtherExp exp ) {
if(exp instanceof ClassItem) {
if(!classes.containsKey(exp)) {
classes.put(exp,computeName((ClassItem)exp,classes));
super.onOther(exp);
}
return;
}
if(exp instanceof PrimitiveItem) {
if(!primitives.containsKey(exp)) {
primitives.put(exp,computeName((PrimitiveItem)exp,primitives));
super.onOther(exp);
}
return;
}
if(exp instanceof FieldItem) {
if(!fields.containsKey(exp)) {
fields.put(exp,computeName((FieldItem)exp,fields));
super.onOther(exp);
}
return;
}
if(exp instanceof IgnoreItem) {
if(!ignores.containsKey(exp)) {
ignores.put(exp,computeName((IgnoreItem)exp,ignores));
super.onOther(exp);
}
return;
}
super.onOther(exp);
}
});
// assign names to intermediate non-terminals.
//====================================================================
copyAll( elements, "E", allNames );
copyAll( attributes, "A", allNames );
copyAll( datatypes, "D", allNames );
copyAll( classes, "C", allNames );
copyAll( fields, "N", allNames );
copyAll( primitives, "P", allNames );
copyAll( ignores, "Ignore", allNames );
final ElementExp[] elms = (ElementExp[])elements.keySet().toArray(new ElementExp[0]);
final AttributeExp[] atts = (AttributeExp[])attributes.keySet().toArray(new AttributeExp[0]);
final DataOrValueExp[] dts = (DataOrValueExp[])datatypes.keySet().toArray(new DataOrValueExp[0]);
final ClassItem[] cis = (ClassItem[])classes.keySet().toArray(new ClassItem[0]);
final FieldItem[] fis = (FieldItem[])fields.keySet().toArray(new FieldItem[0]);
final PrimitiveItem[] pis = (PrimitiveItem[])primitives.keySet().toArray(new PrimitiveItem[0]);
final IgnoreItem[] iis = (IgnoreItem[])ignores.keySet().toArray(new IgnoreItem[0]);
for( int i=0; i rule relationship
out.start("rulesList");
Iterator itr = rules.iterateKeys();
while(itr.hasNext()) {
Expression symbol = (Expression)itr.next();
out.start("nonTerminal",
new String[]{"id",getId(symbol)});
Rule[] rs = rules.getAll(symbol);
for( int i=0; iKohsuke KAWAGUCHI
*/
class XMLGenerator
{
XMLGenerator( AnnotatedGrammar grammar, Symbolizer symbolizer, Controller controller ) {
this.grammar = grammar;
this.symbolizer = symbolizer;
this.controller = controller;
}
private final AnnotatedGrammar grammar;
private final Symbolizer symbolizer;
private final Controller controller;
void generate() throws SAXException, IOException {
try {
ClassItem[] types = grammar.getClasses();
for( int i=0; iKohsuke KAWAGUCHI
*/
public interface ModelGenerator
{
/**
* generate object models.
*/
void generate( AnnotatedGrammar grammar, Symbolizer symbolizer, Controller controller ) throws Exception ;
public static final ModelGenerator xmlGenerator = new ModelGenerator() {
public void generate( AnnotatedGrammar grammar, Symbolizer symbolizer, Controller controller ) throws Exception {
new XMLGenerator(grammar,symbolizer,controller).generate();
}
};
public static final ModelGenerator javaGenerator = new ModelGenerator() {
public void generate( AnnotatedGrammar grammar, Symbolizer symbolizer, Controller controller ) throws Exception {
new ClassSerializer(grammar,symbolizer,controller).generate();
}
};
}
msv-2009.1/tahiti/src/com/sun/tahiti/compiler/Controller.java 0000644 0001750 0001750 00000001625 07326114117 024344 0 ustar giovanni giovanni /*
* @(#)$Id: Controller.java 923 2001-07-20 20:45:03Z Bear $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.tahiti.compiler;
import com.sun.tahiti.grammar.TypeItem;
import com.sun.msv.reader.GrammarReaderController;
import java.io.OutputStream;
import java.io.IOException;
/**
* this interface acts as a controller of various processings.
*
*
* Methods on the GrammarReaderController interface is used for error reporting.
*
* @author
* Kohsuke KAWAGUCHI
*/
public interface Controller extends GrammarReaderController {
/**
* the contents of the specified {@link TypeItem} will be sent
* to the returned DocumentHandler.
*/
OutputStream getOutput( TypeItem type ) throws IOException;
}
msv-2009.1/tahiti/src/com/sun/tahiti/compiler/sm/ 0000755 0001750 0001750 00000000000 11622453065 021773 5 ustar giovanni giovanni msv-2009.1/tahiti/src/com/sun/tahiti/compiler/sm/MarshallerGenerator.java 0000644 0001750 0001750 00000042126 07365333167 026615 0 ustar giovanni giovanni /*
* @(#)$Id: MarshallerGenerator.java 1256 2001-10-23 18:27:03Z Bear $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.tahiti.compiler.sm;
import com.sun.tahiti.compiler.Symbolizer;
import com.sun.tahiti.compiler.XMLWriter;
import com.sun.tahiti.grammar.*;
import com.sun.msv.grammar.*;
import com.sun.msv.grammar.util.ExpressionWalker;
import com.sun.msv.reader.GrammarReaderController;
import org.xml.sax.SAXException;
import org.apache.xml.serialize.XMLSerializer;
import org.apache.xml.serialize.OutputFormat;
import java.io.ByteArrayOutputStream;
import java.util.Set;
import java.util.Iterator;
/**
* generates a simple marhsllaer for a ClassItem.
*
*
* This algorithm cannot generate a marshaller for complex object models.
*
* @author
* Kohsuke KAWAGUCHI
*/
public class MarshallerGenerator implements ExpressionVisitorVoid {
/**
* generates a marshaller for the given ClassItem.
*
*
* Using this method directly is discouraged due to the following reasons.
*
*
*
* This method does NOT call the startDocument/endDocument events
* of the handler. The caller has to invoke them if necessary.
*
* This method could fail even after several fragments are sent
* to a XMLWriter object, by throwing an Abort exception.
* This happens when the object model is
* too compilcated for this algorithm. The caller has to catch it
* and cancel any sideeffects caused by already written fragments.
*
*
*
*
* This method throws an Abort exception if it finds impossible to generate
* a marshaller.
*/
public static void write( Symbolizer symbolizer, ClassItem cls, XMLWriter out,
final GrammarReaderController controller ) {
cls.exp.visit(new MarshallerGenerator(symbolizer,cls,out,controller));
}
/**
* generates a marshaller for the given ClassItem.
*
* @return
* a byte array that contains XML representation of the marshaller.
* null if this method fails to produce a marhsaller.
*/
public static byte[] write( Symbolizer symbolizer, ClassItem cls,
GrammarReaderController controller ) throws SAXException {
try {
ByteArrayOutputStream baos = new ByteArrayOutputStream();
final XMLWriter out = new XMLWriter(
new XMLSerializer(baos,new OutputFormat("xml",null,true) ));
out.handler.startDocument();
write( symbolizer, cls, out, controller );
out.handler.endDocument();
return baos.toByteArray();
} catch ( XMLWriter.SAXWrapper w ) {
throw w.e;
} catch ( Abort a ) {
return null;
}
}
private MarshallerGenerator( Symbolizer symbolizer,
ClassItem cls, XMLWriter out, GrammarReaderController controller) {
this.symbolizer = symbolizer;
this.owner = cls;
this.out = out;
this.controller = controller;
}
private final Symbolizer symbolizer;
private final ClassItem owner;
private final XMLWriter out;
private final GrammarReaderController controller;
/**
* Exception that indicates the object model is too complicated
* to generate a marshaller by this algorithm.
*/
public static class Abort extends RuntimeException {};
/**
* <oneOrMore/> will produce the following marshaller.
*
*
* do {
* marshal body;
* } while( item available );
*
*/
public void onOneOrMore( OneOrMoreExp exp ) {
Set uniqueFields = calcUniqueField( owner.exp, exp );
if( uniqueFields==null ) {
// this class cannot be marshalled.
controller.warning( null,
localize(
UNABLE_TO_PRODUCE_MARSHALLER_ONEORMORE, owner.getTypeName() ));
throw new Abort();
}
if( uniqueFields.size()==0 ) {
// there is no field in this.
// so ignore this .
exp.exp.visit(this);
return;
}
out.start("oneOrMore",new String[]{"while",setToString(uniqueFields)});
exp.exp.visit(this);
out.end("oneOrMore");
}
public void onChoice( ChoiceExp exp ) {
Expression[] children = exp.getChildren();
Expression otherwise = null;
Expression undecidable = null;
if( currentField!=null ) {
/*
if
"this choice is contained in a FieldItem"
and
(
(
"the multiplicity of this field in this ClassItem is at most one"
and
"all the branches are either JavaItem or epsilon"
)
or
"all the branches are JavaItem"
)
then we can produce a simple marshaller.
this works for choices of s/s.
*/
boolean hasEpsilonEdge = false;
boolean fail = false;
boolean hasMarshallableItem = false;
boolean hasPrimitiveItem = false;
// common type of primitives
PrimitiveItem primitiveType = null;
for( int i=0; i
* use caution. Since Expressions are shared, it is possible that the root
* exp contains the branch more than once. For example,
*
*
* root -> SequenceExp(branch,branch)
*
*
* @return
* this method returns null to indicate that there is no unique name.
* Otherwise, this method returns a set
* of the fields which appear in this branch but not elsewhere.
*/
private Set calcUniqueField( Expression root, final Expression branch ) {
final Set branchFields = new java.util.HashSet();
branch.visit( new FieldWalker(currentField){
// this marshaller cannot support AGM that contains a loop
protected void findField( FieldItem field, Type child ) {
branchFields.add( field.name );
}
});
root.visit( new ExpressionVisitorVoid(){
private boolean visitBranch = false;
private FieldItem currentField = null;
public void onOther( OtherExp exp ) {
if(!test(exp)) return;
if( exp instanceof FieldItem ) {
assert( currentField==null );
currentField = (FieldItem)exp;
exp.exp.visit(this);
assert( currentField==exp );
currentField = null;
return;
}
if( exp instanceof ClassItem || exp instanceof InterfaceItem
|| exp instanceof PrimitiveItem ) {
assert( currentField!=null );
if(branchFields.remove( currentField.name )) {
/* System.out.println(currentField.name+" is removed");
System.out.println("owner is "+
com.sun.msv.grammar.util.ExpressionPrinter.printContentModel(owner));
System.out.println("branch is "+branch.toString());
System.out.println(
com.sun.msv.grammar.util.ExpressionPrinter.printContentModel(branch));
Exception e = new Exception();
e.fillInStackTrace();
e.printStackTrace(System.out);
*/ }
return;
}
if( exp instanceof IgnoreItem ) return;
assert(!(exp instanceof JavaItem));
exp.exp.visit(this);
}
public void onChoice( ChoiceExp exp ) { onBinExp(exp); }
public void onSequence( SequenceExp exp ) { onBinExp(exp); }
public void onInterleave( InterleaveExp exp){ onBinExp(exp); }
public void onBinExp( BinaryExp exp ) {
if(test(exp)) {
exp.exp1.visit(this);
exp.exp2.visit(this);
}
}
public void onElement( ElementExp exp ) {
if(test(exp)) exp.contentModel.visit(this);
}
public void onAttribute( AttributeExp exp ) {
if(test(exp)) exp.exp.visit(this);
}
public void onRef( ReferenceExp exp ) {
if(test(exp)) exp.exp.visit(this);
}
public void onOneOrMore( OneOrMoreExp exp ) {
if(test(exp)) exp.exp.visit(this);
}
public void onList( ListExp exp ) {
if(test(exp)) exp.exp.visit(this);
}
public void onEpsilon() {}
private boolean test( Expression exp ) {
if( exp!=branch ) {
/* if( exp instanceof OneOrMoreExp && branch instanceof OneOrMoreExp ) {
try {
System.out.println( exp.toString()+" vs "+branch.toString() );
System.out.println(
((OneOrMoreExp)exp).exp.toString() +" , "+
((OneOrMoreExp)branch).exp.toString() );
FieldItem lhs = (FieldItem)((OneOrMoreExp)exp).exp;
FieldItem rhs = (FieldItem)((OneOrMoreExp)branch).exp;
System.out.println( lhs.name + " : " + rhs.name );
System.out.println( lhs.exp.toString() + " / " + rhs.exp.toString() );
System.out.println(
((InterfaceItem)lhs.exp).name
+ " / " +
((ClassItem)rhs.exp).name );
} catch( Exception e ) {;}
}
*/ return true;
}
if(visitBranch)
// this is the second time to visit the branch.
// that means this branch is contained more than once.
// so there is no unique field.
branchFields.clear();
// by setting branchFields empty, the calcUniqueField method
// will return null.
else
visitBranch = true;
return false;
}
// these primitives should not be used.
public void onMixed( MixedExp exp ) { throw new Error(); }
public void onConcur( ConcurExp exp ) { throw new Error(); }
public void onData( DataExp exp ) { throw new Error(); }
public void onValue( ValueExp exp ) { throw new Error(); }
public void onNullSet() { throw new Error(); }
public void onAnyString() { throw new Error(); }
});
// there is no unique field.
if( branchFields.size()==0 ) return null;
return branchFields;
}
private static void assert( boolean b ) {
if(!b) throw new Error();
}
private static String localize( String prop, Object arg ) {
return localize( prop, new Object[]{arg} );
}
private static String localize( String prop, Object[] args ) {
String format = java.util.ResourceBundle.getBundle(
"com.sun.tahiti.compiler.sm.Messages").getString(prop);
return java.text.MessageFormat.format(format, args );
}
static final String UNABLE_TO_PRODUCE_MARSHALLER_ONEORMORE = // arg:1
"MarshallerGenerator.OneOrMore";
static final String UNABLE_TO_PRODUCE_MARSHALLER_UNDECIDABLE_CHOICE = // arg:1
"MarshallerGenerator.UndecidableChoice";
static final String UNABLE_TO_PRODUCE_MARSHALLER_MULTIPLE_DEFAULTS = // arg:1
"MarshallerGenerator.MultipleDefaults";
static final String UNABLE_TO_PRODUCE_MARSHALLER_IGNOREITEM = // arg:1
"Marshaller.IgnoreItem";
}
msv-2009.1/tahiti/src/com/sun/tahiti/compiler/sm/FieldWalker.java 0000644 0001750 0001750 00000003627 07326114117 025035 0 ustar giovanni giovanni /*
* @(#)$Id: FieldWalker.java 923 2001-07-20 20:45:03Z Bear $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.tahiti.compiler.sm;
import com.sun.tahiti.grammar.*;
import com.sun.msv.grammar.*;
import com.sun.msv.grammar.util.ExpressionWalker;
/**
* traverses an expression tree and reports class items with the field name.
*
* @author
* Kohsuke KAWAGUCHI
*/
abstract class FieldWalker extends ExpressionWalker
{
FieldWalker( FieldItem currentField ) {
this.currentField = currentField;
}
FieldWalker() { this(null); }
private FieldItem currentField;
/**
* this method is called whenever a ClassItem/PrimitiveItem/InterfaceItem
* is found. Note that the same object can be reported more than once,
* with possibly the different name (or the same name).
*
* @param field
* FieldItem object that encapsulates the 'child' object. In other words,
* the 'child' object is stored in this field.
* @param child
* ClassItem, PrimitiveItem, or InterfaceItem object found in
* the expression tree. This is the child object.
*/
protected abstract void findField( FieldItem field, Type child );
public void onOther( OtherExp exp ) {
if( exp instanceof FieldItem ) {
assert(currentField==null);
currentField = (FieldItem)exp;
exp.exp.visit(this);
assert(currentField==exp);
currentField = null;
return;
}
if( exp instanceof ClassItem || exp instanceof InterfaceItem
|| exp instanceof PrimitiveItem ) {
assert(currentField!=null);
findField( currentField, (Type)exp );
return;
}
if( exp instanceof IgnoreItem ) return;
assert(!(exp instanceof JavaItem));
super.onOther(exp);
}
private static void assert( boolean b ) {
if(!b) throw new Error();
}
}
msv-2009.1/tahiti/src/com/sun/tahiti/compiler/sm/MarshallerSerializer.java 0000644 0001750 0001750 00000004675 07326114117 026774 0 ustar giovanni giovanni /*
* @(#)$Id: MarshallerSerializer.java 923 2001-07-20 20:45:03Z Bear $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.tahiti.compiler.sm;
import com.sun.tahiti.grammar.AnnotatedGrammar;
import com.sun.tahiti.grammar.ClassItem;
import com.sun.tahiti.compiler.XMLWriter;
import com.sun.tahiti.compiler.Symbolizer;
import com.sun.tahiti.util.xml.DocumentFilter;
import com.sun.msv.reader.GrammarReaderController;
import org.xml.sax.Parser;
import org.xml.sax.DocumentHandler;
import org.xml.sax.SAXException;
import org.xml.sax.InputSource;
import java.io.ByteArrayInputStream;
import java.io.IOException;
import javax.xml.parsers.ParserConfigurationException;
/**
* serializes all marshallers in the grammar into one XML representation.
*
* @author
* Kohsuke KAWAGUCHI
*/
public class MarshallerSerializer {
public static void serialize(
AnnotatedGrammar grammar, Symbolizer symbolizer, GrammarReaderController controller,
DocumentHandler handler ) throws SAXException,ParserConfigurationException,IOException {
final XMLWriter out = new XMLWriter(handler);
try {
out.handler.startDocument();
out.start("unmarshaller");
Parser parser = javax.xml.parsers.SAXParserFactory.newInstance().newSAXParser().getParser();
ClassItem[] classes = grammar.getClasses();
for( int i=0; iKohsuke KAWAGUCHI
*/
public class XMLWriter {
public final DocumentHandler handler;
public XMLWriter( DocumentHandler handler ) {
this.handler = handler;
}
/** creates a new XMLWriter from a ContentHandler. */
public static XMLWriter fromContentHandler( ContentHandler handler ) {
return new XMLWriter( new ContentHandlerAdaptor(handler) );
}
// primitive write methods
//-----------------------------------------
public void element( String name ) {
element( name, new String[0] );
}
public void element( String name, String[] attributes ) {
start(name,attributes);
end(name);
}
public void element( String name, String contents ) {
start(name);
characters(contents);
end(name);
}
public void start( String name ) {
start(name, new String[0] );
}
public void start( String name, String[] attributes ) {
// create attributes.
AttributeListImpl as = new AttributeListImpl();
for( int i=0; ipackage ; {// symbols private static final LLElementExp ; private static final LLAttributeExp ; private static final IntermediateSymbol = new IntermediateSymbol(""); public static final NamedSymbol = new NamedSymbol(""); public static final DatabindableDatatype ; private static final NonTerminalSymbol = new DefaultNonTerminalSymbol(""); private static final NonTerminalSymbol = new IgnoreSymbol(""); private static final NonTerminalSymbol = new NonTerminalSymbol() {>"; }
}; // all rules private static final Rule[] rules = new Rule[]; // TODO: still leave a lot to be desired = com.sun.msv.datatype.xsd.DatatypeFactory
Unsupported datatype library
.getTypeByName(""); = new LLElementExp( ); // attributes and shared particles. In the same order as in the xml file final Expression = ; = new LLAttributeExp( , ); rules[] = new Rule( new Object[]{ , }, new Filter[]{,Filter.emptyFilternew Filter.SimpleFilter()new Filter.SetFilter(new Object[]{,})}); // element content models .contentModel = ;.parserTable = new Table_(); // set parsing table for attributes .parserTable = new Table_(); // top level final Expression topLevel = ; final LLParserTable rootTable = new Table_(); final Object rootSymbol = ; final LLParserTable rootTable = null; final Object rootSymbol = null; private static final class Table_ implements LLParserTable { private static final Rule[] a = new Rule[]{,rules[]}; public Rule[] get( Object top, Object input ) { if( top== ) { if( input== ) return arules[].selfArray; return rules[].selfArray; } if( top== ) return rules[].selfArray; return null; } };
//
// utility methods
//
public static unmarshall( String source )
throws IOException, SAXException, ParserConfigurationException {
return unmarshall( new InputSource(source) );
}
public static unmarshall( InputSource source )
throws IOException, SAXException, ParserConfigurationException {
return ()
com.sun.tahiti.runtime.ll.Unmarshaller.unmarshall(
.grammar, source );
}
}new SimpleNameClass("","")new ChoiceNameClass(,)new DifferenceNameClass(,)AnyNameClass.theInstancenew NamespaceNameClass("")new NotNameClass()pool.createChoice(,)pool.createInterleave(,)pool.createSequence(,)Expression.epsilonExpression.anyStringpool.createKey(, new StringPair("",""))pool.createKeyref(, new StringPair("",""))pool.createList()pool.createOneOrMore()pool.createData(,emptyName) msv-2009.1/tahiti/src/com/sun/tahiti/compiler/class2java.xsl.unused 0000644 0001750 0001750 00000005326 07314757105 025452 0 ustar giovanni giovanni
public class extends implements , { public []Vector = null = new [] = new java.util.Vector(); msv-2009.1/tahiti/src/com/sun/tahiti/compiler/Driver.java 0000644 0001750 0001750 00000015513 07337343356 023470 0 ustar giovanni giovanni /*
* @(#)$Id: Driver.java 1087 2001-08-18 01:37:50Z Bear $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.tahiti.compiler;
import java.io.File;
import java.io.OutputStream;
import java.io.IOException;
import java.io.FileOutputStream;
import java.util.Map;
import javax.xml.parsers.SAXParserFactory;
import javax.xml.transform.sax.TransformerHandler;
import javax.xml.transform.stream.StreamSource;
import javax.xml.transform.stream.StreamResult;
import com.sun.tahiti.compiler.Controller;
import com.sun.tahiti.compiler.ControllerImpl;
import com.sun.tahiti.compiler.generator.ModelGenerator;
import com.sun.tahiti.compiler.ll.Rules;
import com.sun.tahiti.compiler.ll.RuleSerializer;
import com.sun.tahiti.compiler.ll.RuleGenerator;
import com.sun.tahiti.compiler.sm.MarshallerSerializer;
import com.sun.tahiti.compiler.Symbolizer;
import com.sun.tahiti.grammar.TypeItem;
import com.sun.tahiti.grammar.AnnotatedGrammar;
import com.sun.tahiti.reader.GrammarLoader;
import com.sun.tahiti.util.xml.XSLTUtil;
import com.sun.msv.reader.GrammarReaderController;
import org.apache.xml.serialize.XMLSerializer;
import org.apache.xml.serialize.OutputFormat;
import org.xml.sax.XMLReader;
import org.xml.sax.DocumentHandler;
/**
* Command-line compiler.
*
* @author
* Kohsuke KAWAGUCHI
*/
public class Driver
{
private static class OutputMethod {}
private static final OutputMethod java = new OutputMethod();
private static final OutputMethod xml = new OutputMethod();
private static void usage() {
System.err.println(
"Usage: tahiti \n"+
"[OUTPUT OPTIONS]\n"+
" -out xml compiler will produce xml files.\n"+
" -out java compiler will produce java source files.\n"+
" -d specify output directory.\n"+
"[GENERIC OPTIONS]\n"+
" -package \n"+
" place java files into the specified package.\n"+
"" );
}
public static void main( String args[] ) throws Exception {
System.exit(run(args));
}
public static int run( String args[] ) throws Exception {
// TODO: where should we obtain the package name
// and the file name of the generated grammar?
OutputMethod out = java;
String grammarFileName=null;
File outDir = new File(".");
for( int i=0; i
* This method creates directories if necessary.
*
* @param javaPath
* it will be something like "abc.def.ghi"
*/
private static File getJavaFile( File parent, String javaPath ) {
File r = new File( parent, javaPath.replace('.','/')+".java" );
new File(r.getParent()).mkdirs();
return r;
}
}
msv-2009.1/tahiti/src/com/sun/tahiti/compiler/Symbolizer.java 0000644 0001750 0001750 00000001004 07326114117 024347 0 ustar giovanni giovanni /*
* @(#)$Id: Symbolizer.java 923 2001-07-20 20:45:03Z Bear $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.tahiti.compiler;
/**
* used to resolve various objects to its id so that
* they can be serialized.
*
* @author
* Kohsuke KAWAGUCHI
*/
public interface Symbolizer {
String getId( Object o );
}
msv-2009.1/tahiti/src/com/sun/tahiti/util/ 0000755 0001750 0001750 00000000000 11622453065 020517 5 ustar giovanni giovanni msv-2009.1/tahiti/src/com/sun/tahiti/util/xml/ 0000755 0001750 0001750 00000000000 11622453065 021317 5 ustar giovanni giovanni msv-2009.1/tahiti/src/com/sun/tahiti/util/xml/DOMVisitor.java 0000644 0001750 0001750 00000001754 07326165614 024176 0 ustar giovanni giovanni /*
* @(#)$Id: DOMVisitor.java 932 2001-07-21 02:40:12Z Bear $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.tahiti.util.xml;
import org.w3c.dom.Document;
import org.w3c.dom.Element;
import org.w3c.dom.NodeList;
import org.w3c.dom.Node;
/**
* visits all DOM elements in the depth-first order (in-order).
*
* @author
* Kohsuke KAWAGUCHI
*/
public abstract class DOMVisitor
{
public void visit( Document dom ) {
visit( dom.getDocumentElement() );
}
public void visit( Element e ) {
NodeList lst = e.getChildNodes();
int len = lst.getLength();
for( int i=0; iKohsuke KAWAGUCHI
*/
public class DocumentFilter implements DocumentHandler
{
public DocumentHandler next;
public DocumentFilter( DocumentHandler next ) {
this.next = next;
}
public void startDocument() throws SAXException {
next.startDocument();
}
public void endDocument() throws SAXException {
next.endDocument();
}
public void startElement( String name, AttributeList atts ) throws SAXException {
next.startElement(name,atts);
}
public void endElement( String name ) throws SAXException {
next.endElement(name);
}
public void characters( char[] buf, int start, int len ) throws SAXException {
next.characters(buf,start,len);
}
public void ignorableWhitespace( char[] buf, int start, int len ) throws SAXException {
next.ignorableWhitespace(buf,start,len);
}
public void processingInstruction( String target, String data ) throws SAXException {
next.processingInstruction(target,data);
}
public void setDocumentLocator( Locator loc ) {
next.setDocumentLocator(loc);
}
}
msv-2009.1/tahiti/src/com/sun/tahiti/util/xml/XSLTUtil.java 0000644 0001750 0001750 00000002011 07326114117 023602 0 ustar giovanni giovanni /*
* @(#)$Id: XSLTUtil.java 923 2001-07-20 20:45:03Z Bear $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.tahiti.util.xml;
import javax.xml.transform.TransformerConfigurationException;
import javax.xml.transform.sax.TransformerHandler;
import javax.xml.transform.sax.SAXTransformerFactory;
import javax.xml.transform.stream.StreamSource;
import javax.xml.transform.stream.StreamResult;
/**
* utility methods for XSLT related tasks.
*
* @author
* Kohsuke KAWAGUCHI
*/
public final class XSLTUtil
{
/** gets an XSLT engine. */
public static TransformerHandler getTransformer( java.io.InputStream src )
throws TransformerConfigurationException {
SAXTransformerFactory xsltFactory = new org.apache.xalan.processor.TransformerFactoryImpl();
return xsltFactory.newTransformerHandler(new StreamSource(src));
}
}
msv-2009.1/tahiti/src/com/sun/tahiti/util/xml/SAXEventGenerator.java 0000644 0001750 0001750 00000004531 07326165614 025477 0 ustar giovanni giovanni /*
* @(#)$Id: SAXEventGenerator.java 932 2001-07-21 02:40:12Z Bear $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.tahiti.util.xml;
import org.w3c.dom.Node;
import org.w3c.dom.Attr;
import org.w3c.dom.Element;
import org.w3c.dom.Document;
import org.xml.sax.ContentHandler;
import org.xml.sax.SAXException;
import org.xml.sax.helpers.AttributesImpl;
import org.xml.sax.helpers.LocatorImpl;
/**
* produces SAX2 event from a DOM tree.
*
* @author
* Kohsuke KAWAGUCHI
*/
public class SAXEventGenerator {
/**
* scans the specified DOM and sends SAX2 events to the handler.
*/
public static void parse( Document dom, final ContentHandler handler ) throws SAXException {
DOMVisitor visitor = new DOMVisitor(){
public void visit( Element e ) {
int attLen = e.getAttributes().getLength();
AttributesImpl atts = new AttributesImpl();
for( int i=0; iKohsuke KAWAGUCHI
*/
public class DOMBuilder extends DefaultHandler {
private final Document dom;
private Node parent;
public DOMBuilder( Document document ) {
this.dom = document;
parent = dom;
}
public DOMBuilder() throws ParserConfigurationException {
this( DocumentBuilderFactory.newInstance().newDocumentBuilder().newDocument() );
}
/**
* returns DOM. This method should be called after the parsing was completed.
*/
public Document getDocument() {
return dom;
}
public void startElement( String ns, String local, String qname, Attributes atts ) {
Element e = dom.createElementNS( ns, local );
parent.appendChild(e);
parent = e;
for( int i=0; iKohsuke KAWAGUCHI
*/
public interface Model {
/**
* computes the replacement string for the specified parameter.
* When a format string contains <%abc>, then "abc" is passed
* as a parameter.
*/
String getParameter( String parameter );
}
msv-2009.1/tahiti/src/com/sun/tahiti/util/text/Formatter.java 0000644 0001750 0001750 00000003031 07326114117 024304 0 ustar giovanni giovanni /*
* @(#)$Id: Formatter.java 923 2001-07-20 20:45:03Z Bear $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.tahiti.util.text;
/**
* Text formatter.
*
* @author
* Kohsuke KAWAGUCHI
*/
public class Formatter
{
/**
* formats a text.
*
* acts like java.text.MessageFormat#format, but more flexible.
*
* Each occurence of <%foo> is replaced by the corresponding
* string supplied by a Model object.
*/
public static String format( String fmt, Model model ) {
int idx=0;
StringBuffer out = new StringBuffer();
while( (idx=fmt.indexOf("<%")) >= 0 ) {
out.append( fmt.substring(0,idx) );
fmt = fmt.substring(idx+2);
int last = fmt.indexOf(">");
if(last==-1)
throw new IllegalArgumentException("end tag not found");
String replace = model.getParameter( fmt.substring(0,last) );
out.append(replace);
fmt = fmt.substring(last+1);
}
out.append(fmt);
return out.toString();
}
/**
* simple version of the format method.
*
* This version accepts parameters like <%1> <%2> and replaces
* them by the corresponding item in the array.
*/
public static String format( String fmt, final Object[] args ) {
return format( fmt,
new Model(){
public String getParameter( String arg ) {
return args[Integer.parseInt(arg)].toString();
}
});
}
}
msv-2009.1/tahiti/src/com/sun/tahiti/runtime/ 0000755 0001750 0001750 00000000000 11622453065 021225 5 ustar giovanni giovanni msv-2009.1/tahiti/src/com/sun/tahiti/runtime/ll/ 0000755 0001750 0001750 00000000000 11622453065 021634 5 ustar giovanni giovanni msv-2009.1/tahiti/src/com/sun/tahiti/runtime/ll/NamedSymbol.java 0000644 0001750 0001750 00000001723 07326114117 024712 0 ustar giovanni giovanni /*
* @(#)$Id: NamedSymbol.java 923 2001-07-20 20:45:03Z Bear $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.tahiti.runtime.ll;
/**
* Non-terminal name symbol for LL grammar.
* immutable.
*
* @author
* Kohsuke KAWAGUCHI
*/
public class NamedSymbol extends NonTerminalSymbol
{
public final String name;
public NamedSymbol( String name ) {
this.name = name;
}
public String toString() {
return "N<"+name+">";
}
public LLParser.Receiver createReceiver( final LLParser.Receiver parent ) {
return new LLParser.ObjectReceiver() {
public void start() throws Exception {}
public void end() throws Exception {}
public void action( Object item ) throws Exception {
((LLParser.FieldReceiver)parent).action( item, NamedSymbol.this );
}
};
}
}
msv-2009.1/tahiti/src/com/sun/tahiti/runtime/ll/Debug.java 0000644 0001750 0001750 00000000634 07337072463 023537 0 ustar giovanni giovanni /*
* @(#)$Id: Debug.java 1081 2001-08-17 01:36:51Z Bear $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.tahiti.runtime.ll;
public class Debug
{
/**
* set this field to true to enable debug information.
*/
// public static boolean debug = true;
}
msv-2009.1/tahiti/src/com/sun/tahiti/runtime/ll/BindableGrammar.java 0000644 0001750 0001750 00000001102 07326114117 025476 0 ustar giovanni giovanni /*
* @(#)$Id: BindableGrammar.java 923 2001-07-20 20:45:03Z Bear $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.tahiti.runtime.ll;
/**
* A Grammar object which is capable of performing data-binding.
*
* @author
* Kohsuke KAWAGUCHI
*/
public interface BindableGrammar extends com.sun.msv.grammar.Grammar {
LLParserTable getRootTable();
Object getRootSymbol();
}
msv-2009.1/tahiti/src/com/sun/tahiti/runtime/ll/Unmarshaller.java 0000644 0001750 0001750 00000005424 07337072463 025150 0 ustar giovanni giovanni /*
* @(#)$Id: Unmarshaller.java 1081 2001-08-17 01:36:51Z Bear $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.tahiti.runtime.ll;
import com.sun.tahiti.runtime.sm.MarshallableObject;
import com.sun.msv.grammar.Grammar;
import com.sun.msv.verifier.psvi.TypeDetector;
import com.sun.msv.verifier.regexp.REDocumentDeclaration;
//import com.sun.msv.verifier.ValidityViolation;
import javax.xml.parsers.SAXParserFactory;
import javax.xml.parsers.ParserConfigurationException;
import org.xml.sax.XMLReader;
import org.xml.sax.SAXException;
import org.xml.sax.SAXParseException;
import org.xml.sax.InputSource;
import org.xml.sax.ErrorHandler;
import java.io.IOException;
/**
* controls the overall unmarshalling process.
*
* This class receives type-augmented SAX events and pass it to
* Binder.
*
* @author
* Kohsuke KAWAGUCHI
*/
public class Unmarshaller extends TypeDetector {
private final Binder binder;
public Unmarshaller( BindableGrammar grammar ) {
super( new REDocumentDeclaration(grammar),
new ErrorHandler(){
// throw an exception if any error happens.
public void warning( SAXParseException e ) {}
public void fatalError( SAXParseException e ) throws UnmarshallingException {
throw new UnmarshallingException(e);
}
public void error( SAXParseException e ) throws UnmarshallingException {
throw new UnmarshallingException(e);
}
});
binder = new Binder(grammar);
setContentHandler(binder);
}
public MarshallableObject getResult() {
return (MarshallableObject)binder.getResult();
}
/**
* reads an XML document from the specified location and returns
* the parsed object.
*
*
* This method will use the default XML parser to parse the document.
*/
public static Object unmarshall( BindableGrammar grammar, String xmlDocument )
throws IOException, SAXException, ParserConfigurationException {
return unmarshall( grammar, new InputSource(xmlDocument) );
}
/**
* reads an XML document from the specified InputSource and returns
* the parsed object.
*
*
* This method will use the default XML parser to parse the document.
*/
public static Object unmarshall( BindableGrammar grammar, InputSource xmlDocument )
throws IOException, SAXException, ParserConfigurationException {
SAXParserFactory factory = SAXParserFactory.newInstance();
factory.setNamespaceAware(true);
XMLReader reader = factory.newSAXParser().getXMLReader();
Unmarshaller unmarshaller = new Unmarshaller(grammar);
reader.setContentHandler(unmarshaller);
reader.parse(xmlDocument);
return unmarshaller.getResult();
}
}
msv-2009.1/tahiti/src/com/sun/tahiti/runtime/ll/DefaultNonTerminalSymbol.java 0000644 0001750 0001750 00000002277 07331403631 027424 0 ustar giovanni giovanni /*
* @(#)$Id: DefaultNonTerminalSymbol.java 996 2001-07-31 01:19:21Z Bear $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.tahiti.runtime.ll;
import com.sun.msv.datatype.DatabindableDatatype;
import org.relaxng.datatype.ValidationContext;
/**
* base class of the non-terminal symbols of LL grammar.
*
* @author
* Kohsuke KAWAGUCHI
*/
public class DefaultNonTerminalSymbol extends NonTerminalSymbol {
public DefaultNonTerminalSymbol( String symbolName ) {
this.symbolName = symbolName;
}
private final String symbolName;
public LLParser.Receiver createReceiver( final LLParser.Receiver parent ) {
return new LLParser.CharacterReceiver(){
public void action(DatabindableDatatype dt, String literal, ValidationContext context ) throws Exception {
((LLParser.ObjectReceiver)parent).action(
dt.createJavaObject(literal,context) );
}
public void start() throws Exception {}
public void end() throws Exception {}
};
}
public String toString() { return symbolName; }
} msv-2009.1/tahiti/src/com/sun/tahiti/runtime/ll/LLParserTable.java 0000644 0001750 0001750 00000001314 07326114117 025130 0 ustar giovanni giovanni /*
* @(#)$Id: LLParserTable.java 923 2001-07-20 20:45:03Z Bear $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.tahiti.runtime.ll;
/**
* LL parser table.
*
* @author
* Kohsuke KAWAGUCHI
*/
public interface LLParserTable {
/**
* looks up LL parsing table.
*
* @param symStackTop
* the symbol of the current stack top.
* @param symInput
* the symbol of the current input token.
* @return
* null if there is no rule to apply.
*/
Rule[] get( Object symStackTop, Object symInput );
}
msv-2009.1/tahiti/src/com/sun/tahiti/runtime/ll/Rule.java 0000644 0001750 0001750 00000003462 07337343356 023424 0 ustar giovanni giovanni /*
* @(#)$Id: Rule.java 1087 2001-08-18 01:37:50Z Bear $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.tahiti.runtime.ll;
/**
* one production rule of LL grammar (for example A -> xBCy)
*
* immutable.
*
* @author
* Kohsuke KAWAGUCHI
*/
public class Rule {
/**
* The symbol sequence that forms the right hand side of the rule.
* 'xBCy' in the above example. Mixture of terminal and non-terminal symbols.
*/
public final Object[] right;
/**
* filters that will be used to hide symbols that match the other branches
* of the <interleave>.
*
*
* filters[0] must be always null. filters[1] is used to hide symbols that
* can appear in right[1], and so on.
*
*
* Please note, that the use of interleave has a restriction.
* Specifically, symbols that can appear in each branch must be disjoint.
* See the documentation for details.
*/
public final Filter[] filters;
/**
* If this field is false, then this rule is a ordinary sequence.
* So A -> xyz matchs to xyz but not zyx.
*
* If this field is true, then this rule is an interleave sequence.
* In this case, A->xyz matches to zxy as well as xyz. (but not xxy).
*/
public final boolean isInterleave;
/**
* An array that contains this rule itself.
*/
public final Rule[] selfArray;
/** constructor for a normal rule. */
public Rule( Object[] right ) {
this(right,null);
}
/** constructor for an interleave rule. */
public Rule( Object[] right, Filter[] filters ) {
this.right=right;
this.filters = filters;
this.isInterleave = (filters!=null);
selfArray = new Rule[]{this};
}
}
msv-2009.1/tahiti/src/com/sun/tahiti/runtime/ll/IgnoreSymbol.java 0000644 0001750 0001750 00000000533 07337343356 025122 0 ustar giovanni giovanni package com.sun.tahiti.runtime.ll;
public class IgnoreSymbol extends NonTerminalSymbol {
private final String name;
public IgnoreSymbol( String _name ) {
this.name = _name;
}
public LLParser.Receiver createReceiver( final LLParser.Receiver parent ) {
return LLParser.ignoreReceiver;
}
public String toString() {
return name;
}
};
msv-2009.1/tahiti/src/com/sun/tahiti/runtime/ll/Binder.java 0000644 0001750 0001750 00000015026 07337072463 023715 0 ustar giovanni giovanni /*
* @(#)$Id: Binder.java 1081 2001-08-17 01:36:51Z Bear $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.tahiti.runtime.ll;
import com.sun.msv.datatype.DatabindableDatatype;
import com.sun.msv.grammar.AttributeExp;
import com.sun.msv.grammar.ElementExp;
import com.sun.msv.grammar.NameClassAndExpression;
import com.sun.msv.grammar.Expression;
import com.sun.msv.verifier.psvi.TypedContentHandler;
import org.relaxng.datatype.Datatype;
import org.relaxng.datatype.ValidationContext;
import org.xml.sax.SAXException;
/**
* perform data-binding.
*
* @author Kohsuke KAWAGUCHI
*/
class Binder implements TypedContentHandler {
private static java.io.PrintStream debug = System.out;
Binder() {
this.rootSymbol = null;
this.rootTable = null;
}
/**
* constructor with the root parser table.
*/
Binder( BindableGrammar grammar ) {
this.rootSymbol = grammar.getRootSymbol();
this.rootTable = grammar.getRootTable();
}
/**
* intermediate packet buffer.
* The buffer is expanded on demand.
*/
private Packet[] buffer = new Packet[16];
/** number of packets currently placed in the buffer. */
private int bufLen;
/** index on the buffer that indicates where the current buffer starts. */
private int currentStartPos = 0;
/** index on the buffer that indicates where the content part starts. */
private int currentBodyPos;
// currentStartPos/currentBodyPos stack.
private int[] cpStack = new int[8];
private int depth;
private LLParser parser = new LLParser();
/** validation context object. */
private ValidationContext context;
/**
* the root parser table.
*
* If this field is present, then the LLParser has to be invoked with
* this table and the rootSymbol int the endDocument method.
*/
private final LLParserTable rootTable;
private final Object rootSymbol;
private void initialize() {
depth = 0;
bufLen = 0;
currentStartPos = 0;
currentBodyPos = 0;
}
/** place a packet in the buffer. */
private void pushPacket( Packet p ) {
if( buffer.length==bufLen ) {
// expand buffer
Packet[] newBuf = new Packet[buffer.length*2];
System.arraycopy(buffer,0,newBuf,0,buffer.length);
buffer = newBuf;
}
buffer[bufLen++] = p;
if(debug!=null) debug.println("pushPacket()");
}
public void characterChunk( String literal, Datatype type ) throws SAXException {
System.out.println("characterChunk()");
assert( type instanceof DatabindableDatatype );
pushPacket( new Packet.DataPacket((DatabindableDatatype)type,literal) );
}
private void processItem( Object targetSymbol, LLParserTable table ) throws SAXException {
// TODO: avoid unnecessary copy.
Packet[] tokens = new Packet[bufLen-currentBodyPos];
System.arraycopy(buffer,currentBodyPos,tokens,0,tokens.length);
Packet[] attributes = new Packet[currentBodyPos-currentStartPos];
System.arraycopy(buffer,currentStartPos,attributes,0,attributes.length);
if( debug!=null ) {
debug.println("target symbol - " + LLParser.symbolToStr(targetSymbol) );
debug.println("input packets (body:"+(bufLen-currentBodyPos)+") (atts:"+(currentBodyPos-currentStartPos)+")");
}
popContext();
try {
// unmarshall this content model and put the result to the buffer.
pushPacket( parser.unmarshall(
targetSymbol, tokens, attributes, context, table ) );
} catch( Exception e ) {
e.printStackTrace();
throw new UnmarshallingException(e);
}
if( debug!=null )
debug.println("item processed ("+
((Packet.ItemPacket)buffer[bufLen-1]).getPayloadSize()
+")\n");
}
/** push the current pointers. */
private void pushContext() {
if( depth==cpStack.length ) {
// expand buffer
int[] newcp = new int[cpStack.length*2];
System.arraycopy(cpStack,0,newcp,0,cpStack.length);
cpStack = newcp;
}
cpStack[depth++] = currentStartPos;
cpStack[depth++] = currentBodyPos;
currentStartPos = bufLen;
currentBodyPos = 0;
}
/** pop the current pointers. */
private void popContext() {
bufLen = currentStartPos;
currentBodyPos = cpStack[--depth];
currentStartPos = cpStack[--depth];
}
public void startElement( String namespaceURI, String localName, String qName ) throws SAXException {
if(debug!=null)
debug.println("startElement("+namespaceURI+","+localName+")");
pushContext();
}
public void startAttribute( String namespaceURI, String localName, String qName ) throws SAXException {
if(debug!=null)
debug.println("startAttribute("+namespaceURI+","+localName+")");
pushContext();
currentBodyPos = bufLen;
if(debug!=null)
debug.println("startAttribute(): currentBodyPos="+currentBodyPos);
}
public void endAttribute( String namespaceURI, String localName, String qName, AttributeExp type ) throws SAXException {
assert( type instanceof LLAttributeExp );
processItem( type, ((LLAttributeExp)type).parserTable );
}
public void endAttributePart() throws SAXException {
currentBodyPos = bufLen;
if(debug!=null) {
debug.println("endAttributePart() (currentBodyPos="+currentBodyPos+")");
}
}
public void endElement( String namespaceURI, String localName, String qName, ElementExp type ) throws SAXException {
assert( type instanceof LLElementExp );
processItem( type, ((LLElementExp)type).parserTable );
}
public void startDocument( ValidationContext _context ) throws SAXException {
initialize();
if( rootSymbol!=null )
pushContext();
this.context = _context;
}
public void endDocument() throws SAXException {
if( rootSymbol!=null )
// we have a root parser table.
// the last invokation.
processItem( rootSymbol, rootTable );
assert( bufLen==1 );
}
public Object getResult() {
// after the completion of a parsing,
// buffer must have one and only one packet, and it must be an ItemPacket.
Packet.ItemPacket top = (Packet.ItemPacket)buffer[0];
final Object[] theResult = new Object[1];
try {
top.dispatch(
new LLParser.ObjectReceiver(){
public void start() {}
public void end() {}
public void action(Object item) {
if(theResult[0]!=null) // the top-level class must be unique.
throw new Error();
theResult[0] = item;
}
}, null );
}catch(Exception e) {
e.printStackTrace();
assert(false); // impossible. because we don't throw any exception from the action.
}
return theResult[0];
}
private static void assert( boolean b ) {
if(!b) throw new Error();
}
}
msv-2009.1/tahiti/src/com/sun/tahiti/runtime/ll/UnmarshallingException.java 0000644 0001750 0001750 00000001211 07326114117 027153 0 ustar giovanni giovanni /*
* @(#)$Id: UnmarshallingException.java 923 2001-07-20 20:45:03Z Bear $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.tahiti.runtime.ll;
/**
* signals an error encountered during the unmarshalling.
*
* @author
* Kohsuke KAWAGUCHI
*/
public class UnmarshallingException extends org.xml.sax.SAXException {
public UnmarshallingException( Exception e ) {
super(e);
}
public UnmarshallingException( String msg ) {
super(msg);
}
}
msv-2009.1/tahiti/src/com/sun/tahiti/runtime/ll/IntermediateSymbol.java 0000644 0001750 0001750 00000002130 07326114117 026271 0 ustar giovanni giovanni /*
* @(#)$Id: IntermediateSymbol.java 923 2001-07-20 20:45:03Z Bear $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.tahiti.runtime.ll;
import com.sun.msv.datatype.DatabindableDatatype;
import org.relaxng.datatype.ValidationContext;
/**
* Intermediate non-terminal symbols for LL grammar.
*
* Intermediate non-terminals are non-terminals with no associated action.
*
* @author
* Kohsuke KAWAGUCHI
*/
public final class IntermediateSymbol extends NonTerminalSymbol
{
/** purely for the debug purpose. */
public final String identifier;
public IntermediateSymbol( String identifier ) {
this.identifier = identifier;
}
public String toString() {
return identifier;
}
/**
* Intermediate non-terminal does not have its own action.
*/
public LLParser.Receiver createReceiver( final LLParser.Receiver parent ) {
// so it can simply return the parent receiver.
return parent;
}
}
msv-2009.1/tahiti/src/com/sun/tahiti/runtime/ll/NonTerminalSymbol.java 0000644 0001750 0001750 00000001426 07326114117 026114 0 ustar giovanni giovanni /*
* @(#)$Id: NonTerminalSymbol.java 923 2001-07-20 20:45:03Z Bear $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.tahiti.runtime.ll;
/**
* base class of the non-terminal symbols of LL grammar.
*
* @author
* Kohsuke KAWAGUCHI
*/
public abstract class NonTerminalSymbol {
public abstract LLParser.Receiver createReceiver( LLParser.Receiver parent );
/**
* the derived class should implement the toString method.
* This method is expected to produce the small (10-15 characters) strings
* like C<String> or N<name>.
*/
public abstract String toString();
}
msv-2009.1/tahiti/src/com/sun/tahiti/runtime/ll/Packet.java 0000644 0001750 0001750 00000006754 07337072463 023731 0 ustar giovanni giovanni /*
* @(#)$Id: Packet.java 1081 2001-08-17 01:36:51Z Bear $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.tahiti.runtime.ll;
//import org.relaxng.datatype.Datatype;
import org.relaxng.datatype.ValidationContext;
import com.sun.msv.datatype.DatabindableDatatype;
import com.sun.msv.grammar.NameClassAndExpression;
/**
* packet is a pair of symbol and payload.
*
* @author
* Kohsuke KAWAGUCHI
*/
abstract class Packet {
public final Object symbol;
Packet( Object symbol ) {
this.symbol = symbol;
}
/** dispatches the content of this packet to the specified receiver. */
public abstract void dispatch( LLParser.Receiver rcv, ValidationContext context ) throws Exception;
/**
* packet for datatype.
*/
static class DataPacket extends Packet {
private final String contents;
DataPacket( DatabindableDatatype symbol, String _contents ) {
super(symbol);
this.contents = _contents;
}
public void dispatch( LLParser.Receiver rcv, ValidationContext context ) throws Exception {
((LLParser.CharacterReceiver)rcv).action( (DatabindableDatatype)super.symbol, contents, context );
}
}
/**
* packet for element and attribute.
*
* this type of packet have multiple items as the payload, and there are
* two types of the payload: the first is the "named" item, which should
* be received by a FieldReceiver; the second is the "unnamed" item, which
* should be received by a ObjectReceiver.
*/
static class ItemPacket extends Packet implements
LLParser.FieldReceiver, LLParser.ObjectReceiver, LLParser.CharacterReceiver {
private static abstract class Payload {
abstract void dispatch( LLParser.Receiver rcv ) throws Exception;
}
private Payload[] payload = new Payload[4];
private int payloadSize = 0;
public int getPayloadSize() { return payloadSize; }
/**
* symbol is usually either LLAttributeExp or LLElementExp.
*/
ItemPacket( Object symbol ) {
super(symbol);
}
public void dispatch( LLParser.Receiver rcv, ValidationContext contest ) throws Exception {
for( int i=0; iKohsuke KAWAGUCHI
*/
public class LLAttributeExp extends AttributeExp {
/** LL parser table for this rule. */
public LLParserTable parserTable;
public LLAttributeExp( NameClass nc, Expression body ) {
super(nc,body);
}
public boolean equals( Object rhs ) {
return this==rhs;
}
}
msv-2009.1/tahiti/src/com/sun/tahiti/runtime/ll/LLElementExp.java 0000644 0001750 0001750 00000001467 07326114117 025003 0 ustar giovanni giovanni /*
* @(#)$Id: LLElementExp.java 923 2001-07-20 20:45:03Z Bear $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.tahiti.runtime.ll;
import com.sun.msv.grammar.NameClass;
import com.sun.msv.grammar.Expression;
import com.sun.msv.grammar.trex.ElementPattern;
/**
* ElementExp with LL parser table.
*
* @author
* Kohsuke KAWAGUCHI
*/
public class LLElementExp extends ElementPattern {
/** LL parser table for this rule. */
public LLParserTable parserTable;
public LLElementExp( NameClass nc ) {
this(nc,Expression.nullSet);
}
public LLElementExp( NameClass nc, Expression body ) {
super(nc,body);
}
}
msv-2009.1/tahiti/src/com/sun/tahiti/runtime/ll/Filter.java 0000644 0001750 0001750 00000002314 07337072463 023733 0 ustar giovanni giovanni package com.sun.tahiti.runtime.ll;
import java.util.Set;
/**
* Input token filter for parsing interleave content models.
*
* This class filters out tokens so that "interleave" can be treated like a sequence.
*
* @author Kohsuke KAWAGUCHI
*/
public interface Filter {
boolean rejects( Object symbol );
/**
* Filter class that rejects only one token.
*/
public static final class SimpleFilter implements Filter {
public SimpleFilter( Object symbol ) { this.symbol=symbol; }
private Object symbol;
public boolean rejects( Object symbol ) {
return symbol==this.symbol;
}
}
/**
* Filter class that rejects tokens by using a set.
*/
public static final class SetFilter implements Filter {
public SetFilter( Object[] _symbols ) {
symbols = new java.util.HashSet();
for( int i=0; i<_symbols.length; i++ )
symbols.add(_symbols[i]);
}
private final Set symbols;
public boolean rejects( Object symbol ) {
return symbols.contains(symbol);
}
}
/** a filter object that rejects nothing. */
public static final Filter emptyFilter = new Filter() {
public boolean rejects( Object symbol ) { return false; }
};
}
msv-2009.1/tahiti/src/com/sun/tahiti/runtime/ll/LLParser.java 0000644 0001750 0001750 00000045645 07337343356 024212 0 ustar giovanni giovanni /*
* @(#)$Id: LLParser.java 1087 2001-08-18 01:37:50Z Bear $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.tahiti.runtime.ll;
import com.sun.msv.datatype.DatabindableDatatype;
import com.sun.msv.grammar.NameClassAndExpression;
import org.relaxng.datatype.ValidationContext;
import java.util.Vector;
import java.util.Set;
import java.util.Map;
/**
* Generic LL parser.
*
* parses tokens according to the specified LL grammar.
*
*
Parser symbols
*
* Terminals
* ---------
* ElementSymbol -- ElementExp
* AttributeSymbol -- AttributeExp
* DataSymbol -- org.relaxng.datatype.DataType
*
* Non-terminals (extends NonTerminalSymbol)
* -----------------------------------------
* ClassSymbol -- ClassSymbol
* NamedSymbol -- NamedSymbol
* IntermediateSymbol -- IntermediateSymbol
*
* ???: It may be possible that we want to have two distinct ClassSymbols whose
* Java type is equal.
*
*
This section shows LL parser tables for each start symbol.
The red input tokens are ambiguous tokens. There are more than one
valid expansion for that token.
(root)
this rule is expanded
... when the token is one of these
, color:redotherwise
-> msv-2009.1/testRepository/ 0000755 0001750 0001750 00000000000 11622453065 015703 5 ustar giovanni giovanni msv-2009.1/readme.html 0000644 0001750 0001750 00000007747 11213774475 014775 0 ustar giovanni giovanni
Read me for MSV developers
ReadMe for MSV development
by Kohsuke KAWAGUCHI
Directory structure
MSV consists of a number of sub projects.
Each sub projects has its own directory, its own build script, etc.
xsdlib
Sun XML Datatypes Library. An implementation of W3C XML Schema Part 2.
testharness
Test harness that is used to parse composite test suite files (.ssuite).
msv
Sun Multi-Schema XML Validator. A schema model and validator implementation. Dependent on XSDLib and test harness.
rngconverter
Sun RELAX NG Converter. reads a schema and produces an equivalent RELAX NG schema. Dependent on MSV.
generator
Sun XML Instance Generator. A tool that produces valid XML documents by reading a schema. Dependent on MSV.
relames
Sun Multi-Schema XML Validator Schematron add-on. An experimental implementation of RELAX NG + Schematron validation. Dependent on MSV.
sox2rng
SOX to RELAX NG converter. Dependent on MSV.
tahiti
Data-binding implementation
trexconverter
TREX Converter. Reads a schema and produces an equivalent TREX pattern.
This project is no longer maintained.
There are several other directories which are used to store other materials.
shared
keeps shared information among multiple subprojects.
testCases
keeps test instances/schemas.
Sub-project structure
Most of the sub projects have a similar directory structure.
src
keeps source files. Files in this directory will be included
in the release package.
test
keeps test files. Files in this directory will NOT be included
in the release package. JUnit is used throughout the project,
and every test code must have "Test.java" as suffix to be recognized
as a test.
bin
keeps the compiled .class files. both "test" and "src" are
compiled into this directory.
doc
release documentation. Files in this directory will be included
in the release package.
Build instruction
To build the entire project, use Ant. The build script also contains the "release" target,
which builds the release packages for all sub projects in a proper order.
When preparing release packages, it is a good idea to use this target
so that dependencies are processed correctly. (But you should run a project-local "release" first to make sure that there is no error in the repository.)
Project-wise build
When you are working on a sub project, you can use the project-local build script. Most of the build scripts are similar, and usually they have
following targets.
binary (default)
compiles everything into bin
javadoc
generates javadoc from the working copy.
Useful to check the documentation.
dist
makes a distribution package in the dist/ directory.
release
Compresses the result of the dist target into a single zip file
and put it to the package/ directory.
msv-2009.1/xsdlib/ 0000755 0001750 0001750 00000000000 11622453066 014112 5 ustar giovanni giovanni msv-2009.1/xsdlib/pom.xml 0000644 0001750 0001750 00000011635 11213776216 015436 0 ustar giovanni giovanni
4.0.0com.sun.msv.datatype.xsdxsdlib2009.1MSV XML Schema Librarynet.java.dev.msvmsv-parent2009.1../parent/pom.xmlXML Schema datatypes libraryscm:svn:http://msv.dev.java.net/svn/msv/tags/msv-2009.1/xsdlibscm:svn:https://msv.dev.java.net/svn/msv/tags/msv-2009.1/xsdlibUsers Listusers-subscribe@msv.dev.java.netusers-unsubscribe@msv.dev.java.nethttps://msv.dev.java.net/servlets/SummarizeList?listName=userssrc**/*.propertiessrc-apache**/*.javaorg.apache.maven.pluginsmaven-jar-plugintest-jarcom.sun.msv.datatype.xsd.CommandLineTesterorg.codehaus.mojobuild-helper-maven-pluginadd-sourcegenerate-sourcesadd-sourcesrc-apachekohsukeKohsuke Kawaguchikk@kohsuke.orgisorelaxisorelaxrelaxngDatatyperelaxngDatatypexercesxercesImpltruejunitjunittestjdomjdomtest
msv-2009.1/xsdlib/resource/ 0000755 0001750 0001750 00000000000 11622453065 015740 5 ustar giovanni giovanni msv-2009.1/xsdlib/resource/META-INF/ 0000755 0001750 0001750 00000000000 11622453065 017100 5 ustar giovanni giovanni msv-2009.1/xsdlib/resource/META-INF/services/ 0000755 0001750 0001750 00000000000 11622453065 020723 5 ustar giovanni giovanni msv-2009.1/xsdlib/resource/META-INF/services/org.relaxng.datatype.DatatypeLibraryFactory 0000644 0001750 0001750 00000000064 10555772151 031341 0 ustar giovanni giovanni com.sun.msv.datatype.xsd.ngimpl.DataTypeLibraryImpl
msv-2009.1/xsdlib/xsdlib.iml 0000644 0001750 0001750 00000003617 10555773215 016116 0 ustar giovanni giovanni
msv-2009.1/xsdlib/build.xml 0000644 0001750 0001750 00000014753 10555773157 015757 0 ustar giovanni giovanni
version=${DSTAMP}importing to CVS...
msv-2009.1/xsdlib/src-apache/ 0000755 0001750 0001750 00000000000 11622453065 016117 5 ustar giovanni giovanni msv-2009.1/xsdlib/src-apache/com/ 0000755 0001750 0001750 00000000000 11622453065 016675 5 ustar giovanni giovanni msv-2009.1/xsdlib/src-apache/com/sun/ 0000755 0001750 0001750 00000000000 11622453065 017502 5 ustar giovanni giovanni msv-2009.1/xsdlib/src-apache/com/sun/msv/ 0000755 0001750 0001750 00000000000 11622453065 020307 5 ustar giovanni giovanni msv-2009.1/xsdlib/src-apache/com/sun/msv/datatype/ 0000755 0001750 0001750 00000000000 11622453065 022122 5 ustar giovanni giovanni msv-2009.1/xsdlib/src-apache/com/sun/msv/datatype/regexp/ 0000755 0001750 0001750 00000000000 11622453065 023414 5 ustar giovanni giovanni msv-2009.1/xsdlib/src-apache/com/sun/msv/datatype/regexp/RegexParser.java 0000644 0001750 0001750 00000126017 10466724046 026522 0 ustar giovanni giovanni /*
* The Apache Software License, Version 1.1
*
*
* Copyright (c) 1999-2003 The Apache Software Foundation. All rights
* reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
*
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
*
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in
* the documentation and/or other materials provided with the
* distribution.
*
* 3. The end-user documentation included with the redistribution,
* if any, must include the following acknowledgment:
* "This product includes software developed by the
* Apache Software Foundation (http://www.apache.org/)."
* Alternately, this acknowledgment may appear in the software itself,
* if and wherever such third-party acknowledgments normally appear.
*
* 4. The names "Xerces" and "Apache Software Foundation" must
* not be used to endorse or promote products derived from this
* software without prior written permission. For written
* permission, please contact apache@apache.org.
*
* 5. Products derived from this software may not be called "Apache",
* nor may "Apache" appear in their name, without prior written
* permission of the Apache Software Foundation.
*
* THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESSED OR IMPLIED
* WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
* OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
* DISCLAIMED. IN NO EVENT SHALL THE APACHE SOFTWARE FOUNDATION OR
* ITS CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
* SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
* LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF
* USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
* ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
* OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT
* OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
* SUCH DAMAGE.
* ====================================================================
*
* This software consists of voluntary contributions made by many
* individuals on behalf of the Apache Software Foundation and was
* originally based on software copyright (c) 1999, International
* Business Machines, Inc., http://www.apache.org. For more
* information on the Apache Software Foundation, please see
* .
*/
package com.sun.msv.datatype.regexp;
import java.util.Locale;
import java.util.MissingResourceException;
import java.util.ResourceBundle;
import java.util.Vector;
/**
* A Regular Expression Parser.
*
* @version RegexParser.java,v 1.8 2003/03/25 14:47:06 sandygao Exp
*/
class RegexParser {
static final int T_CHAR = 0;
static final int T_EOF = 1;
static final int T_OR = 2; // '|'
static final int T_STAR = 3; // '*'
static final int T_PLUS = 4; // '+'
static final int T_QUESTION = 5; // '?'
static final int T_LPAREN = 6; // '('
static final int T_RPAREN = 7; // ')'
static final int T_DOT = 8; // '.'
static final int T_LBRACKET = 9; // '['
static final int T_BACKSOLIDUS = 10; // '\'
static final int T_CARET = 11; // '^'
static final int T_DOLLAR = 12; // '$'
static final int T_LPAREN2 = 13; // '(?:'
static final int T_LOOKAHEAD = 14; // '(?='
static final int T_NEGATIVELOOKAHEAD = 15; // '(?!'
static final int T_LOOKBEHIND = 16; // '(?<='
static final int T_NEGATIVELOOKBEHIND = 17; // '(?'
static final int T_SET_OPERATIONS = 19; // '(?['
static final int T_POSIX_CHARCLASS_START = 20; // '[:' in a character class
static final int T_COMMENT = 21; // '(?#'
static final int T_MODIFIERS = 22; // '(?' [\-,a-z,A-Z]
static final int T_CONDITION = 23; // '(?('
static final int T_XMLSCHEMA_CC_SUBTRACTION = 24; // '-[' in a character class
static class ReferencePosition {
int refNumber;
int position;
ReferencePosition(int n, int pos) {
this.refNumber = n;
this.position = pos;
}
}
int offset;
String regex;
int regexlen;
int options;
ResourceBundle resources;
int chardata;
int nexttoken;
static protected final int S_NORMAL = 0;
static protected final int S_INBRACKETS = 1;
static protected final int S_INXBRACKETS = 2;
int context = S_NORMAL;
int parennumber = 1;
boolean hasBackReferences;
Vector references = null;
public RegexParser() {
this.setLocale(Locale.getDefault());
}
public RegexParser(Locale locale) {
this.setLocale(locale);
}
public void setLocale(Locale locale) {
try {
this.resources = ResourceBundle.getBundle(
getClass().getPackage().getName()+".message", locale);
} catch (MissingResourceException mre) {
throw new RuntimeException("Installation Problem??? Couldn't load messages: "
+mre.getMessage());
}
}
final ParseException ex(String key, int loc) {
return new ParseException(this.resources.getString(key), loc);
}
private final boolean isSet(int flag) {
return (this.options & flag) == flag;
}
synchronized Token parse(String regex, int options) throws ParseException {
this.options = options;
this.offset = 0;
this.setContext(S_NORMAL);
this.parennumber = 1;
this.hasBackReferences = false;
this.regex = regex;
if (this.isSet(RegularExpression.EXTENDED_COMMENT))
this.regex = REUtil.stripExtendedComment(this.regex);
this.regexlen = this.regex.length();
this.next();
Token ret = this.parseRegex();
if (this.offset != this.regexlen)
throw ex("parser.parse.1", this.offset);
if (this.references != null) {
for (int i = 0; i < this.references.size(); i ++) {
ReferencePosition position = (ReferencePosition)this.references.elementAt(i);
if (this.parennumber <= position.refNumber)
throw ex("parser.parse.2", position.position);
}
this.references.removeAllElements();
}
return ret;
}
/*
public RegularExpression createRegex(String regex, int options) throws ParseException {
Token tok = this.parse(regex, options);
return new RegularExpression(regex, tok, this.parennumber, this.hasBackReferences, options);
}
*/
protected final void setContext(int con) {
this.context = con;
}
final int read() {
return this.nexttoken;
}
final void next() {
if (this.offset >= this.regexlen) {
this.chardata = -1;
this.nexttoken = T_EOF;
return;
}
int ret;
int ch = this.regex.charAt(this.offset++);
this.chardata = ch;
if (this.context == S_INBRACKETS) {
// In a character class, this.chardata has one character, that is to say,
// a pair of surrogates is composed and stored to this.chardata.
switch (ch) {
case '\\':
ret = T_BACKSOLIDUS;
if (this.offset >= this.regexlen)
throw ex("parser.next.1", this.offset-1);
this.chardata = this.regex.charAt(this.offset++);
break;
case '-':
if (this.isSet(RegularExpression.XMLSCHEMA_MODE)
&& this.offset < this.regexlen && this.regex.charAt(this.offset) == '[') {
this.offset++;
ret = T_XMLSCHEMA_CC_SUBTRACTION;
} else
ret = T_CHAR;
break;
case '[':
if (!this.isSet(RegularExpression.XMLSCHEMA_MODE)
&& this.offset < this.regexlen && this.regex.charAt(this.offset) == ':') {
this.offset++;
ret = T_POSIX_CHARCLASS_START;
break;
} // Through down
default:
if (REUtil.isHighSurrogate(ch) && this.offset < this.regexlen) {
int low = this.regex.charAt(this.offset);
if (REUtil.isLowSurrogate(low)) {
this.chardata = REUtil.composeFromSurrogates(ch, low);
this.offset ++;
}
}
ret = T_CHAR;
}
this.nexttoken = ret;
return;
}
switch (ch) {
case '|': ret = T_OR; break;
case '*': ret = T_STAR; break;
case '+': ret = T_PLUS; break;
case '?': ret = T_QUESTION; break;
case ')': ret = T_RPAREN; break;
case '.': ret = T_DOT; break;
case '[': ret = T_LBRACKET; break;
case '^': ret = T_CARET; break;
// case '$': ret = T_DOLLAR; break;
case '(':
ret = T_LPAREN;
if (this.offset >= this.regexlen)
break;
if (this.regex.charAt(this.offset) != '?')
break;
if (++this.offset >= this.regexlen)
throw ex("parser.next.2", this.offset-1);
ch = this.regex.charAt(this.offset++);
switch (ch) {
case ':': ret = T_LPAREN2; break;
case '=': ret = T_LOOKAHEAD; break;
case '!': ret = T_NEGATIVELOOKAHEAD; break;
case '[': ret = T_SET_OPERATIONS; break;
case '>': ret = T_INDEPENDENT; break;
case '<':
if (this.offset >= this.regexlen)
throw ex("parser.next.2", this.offset-3);
ch = this.regex.charAt(this.offset++);
if (ch == '=') {
ret = T_LOOKBEHIND;
} else if (ch == '!') {
ret = T_NEGATIVELOOKBEHIND;
} else
throw ex("parser.next.3", this.offset-3);
break;
case '#':
while (this.offset < this.regexlen) {
ch = this.regex.charAt(this.offset++);
if (ch == ')') break;
}
if (ch != ')')
throw ex("parser.next.4", this.offset-1);
ret = T_COMMENT;
break;
default:
if (ch == '-' || 'a' <= ch && ch <= 'z' || 'A' <= ch && ch <= 'Z') {// Options
this.offset --;
ret = T_MODIFIERS;
break;
} else if (ch == '(') { // conditional
ret = T_CONDITION; // this.offsets points the next of '('.
break;
}
throw ex("parser.next.2", this.offset-2);
}
break;
case '\\':
ret = T_BACKSOLIDUS;
if (this.offset >= this.regexlen)
throw ex("parser.next.1", this.offset-1);
this.chardata = this.regex.charAt(this.offset++);
break;
default:
ret = T_CHAR;
}
this.nexttoken = ret;
}
/**
* regex ::= term (`|` term)*
* term ::= factor+
* factor ::= ('^' | '$' | '\A' | '\Z' | '\z' | '\b' | '\B' | '\<' | '\>'
* | atom (('*' | '+' | '?' | minmax ) '?'? )?)
* | '(?=' regex ')' | '(?!' regex ')' | '(?<=' regex ')' | '(?<!' regex ')'
* atom ::= char | '.' | range | '(' regex ')' | '(?:' regex ')' | '\' [0-9]
* | '\w' | '\W' | '\d' | '\D' | '\s' | '\S' | category-block
*/
Token parseRegex() throws ParseException {
Token tok = this.parseTerm();
Token parent = null;
while (this.read() == T_OR) {
this.next(); // '|'
if (parent == null) {
parent = Token.createUnion();
parent.addChild(tok);
tok = parent;
}
tok.addChild(this.parseTerm());
}
return tok;
}
/**
* term ::= factor+
*/
Token parseTerm() throws ParseException {
int ch = this.read();
if (ch == T_OR || ch == T_RPAREN || ch == T_EOF) {
return Token.createEmpty();
} else {
Token tok = this.parseFactor();
Token concat = null;
while ((ch = this.read()) != T_OR && ch != T_RPAREN && ch != T_EOF) {
if (concat == null) {
concat = Token.createConcat();
concat.addChild(tok);
tok = concat;
}
concat.addChild(this.parseFactor());
//tok = Token.createConcat(tok, this.parseFactor());
}
return tok;
}
}
// ----------------------------------------------------------------
Token processCaret() throws ParseException {
this.next();
return Token.token_linebeginning;
}
Token processDollar() throws ParseException {
this.next();
return Token.token_lineend;
}
Token processLookahead() throws ParseException {
this.next();
Token tok = Token.createLook(Token.LOOKAHEAD, this.parseRegex());
if (this.read() != T_RPAREN) throw ex("parser.factor.1", this.offset-1);
this.next(); // ')'
return tok;
}
Token processNegativelookahead() throws ParseException {
this.next();
Token tok = Token.createLook(Token.NEGATIVELOOKAHEAD, this.parseRegex());
if (this.read() != T_RPAREN) throw ex("parser.factor.1", this.offset-1);
this.next(); // ')'
return tok;
}
Token processLookbehind() throws ParseException {
this.next();
Token tok = Token.createLook(Token.LOOKBEHIND, this.parseRegex());
if (this.read() != T_RPAREN) throw ex("parser.factor.1", this.offset-1);
this.next(); // ')'
return tok;
}
Token processNegativelookbehind() throws ParseException {
this.next();
Token tok = Token.createLook(Token.NEGATIVELOOKBEHIND, this.parseRegex());
if (this.read() != T_RPAREN) throw ex("parser.factor.1", this.offset-1);
this.next(); // ')'
return tok;
}
Token processBacksolidus_A() throws ParseException {
this.next();
return Token.token_stringbeginning;
}
Token processBacksolidus_Z() throws ParseException {
this.next();
return Token.token_stringend2;
}
Token processBacksolidus_z() throws ParseException {
this.next();
return Token.token_stringend;
}
Token processBacksolidus_b() throws ParseException {
this.next();
return Token.token_wordedge;
}
Token processBacksolidus_B() throws ParseException {
this.next();
return Token.token_not_wordedge;
}
Token processBacksolidus_lt() throws ParseException {
this.next();
return Token.token_wordbeginning;
}
Token processBacksolidus_gt() throws ParseException {
this.next();
return Token.token_wordend;
}
Token processStar(Token tok) throws ParseException {
this.next();
if (this.read() == T_QUESTION) {
this.next();
return Token.createNGClosure(tok);
} else
return Token.createClosure(tok);
}
Token processPlus(Token tok) throws ParseException {
// X+ -> XX*
this.next();
if (this.read() == T_QUESTION) {
this.next();
return Token.createConcat(tok, Token.createNGClosure(tok));
} else
return Token.createConcat(tok, Token.createClosure(tok));
}
Token processQuestion(Token tok) throws ParseException {
// X? -> X|
this.next();
Token par = Token.createUnion();
if (this.read() == T_QUESTION) {
this.next();
par.addChild(Token.createEmpty());
par.addChild(tok);
} else {
par.addChild(tok);
par.addChild(Token.createEmpty());
}
return par;
}
boolean checkQuestion(int off) {
return off < this.regexlen && this.regex.charAt(off) == '?';
}
Token processParen() throws ParseException {
this.next();
int p = this.parennumber++;
Token tok = Token.createParen(this.parseRegex(), p);
if (this.read() != T_RPAREN) throw ex("parser.factor.1", this.offset-1);
this.next(); // Skips ')'
return tok;
}
Token processParen2() throws ParseException {
this.next();
Token tok = Token.createParen(this.parseRegex(), 0);
if (this.read() != T_RPAREN) throw ex("parser.factor.1", this.offset-1);
this.next(); // Skips ')'
return tok;
}
Token processCondition() throws ParseException {
// this.offset points the next of '('
if (this.offset+1 >= this.regexlen) throw ex("parser.factor.4", this.offset);
// Parses a condition.
int refno = -1;
Token condition = null;
int ch = this.regex.charAt(this.offset);
if ('1' <= ch && ch <= '9') {
refno = ch-'0';
this.hasBackReferences = true;
if (this.references == null) this.references = new Vector();
this.references.addElement(new ReferencePosition(refno, this.offset));
this.offset ++;
if (this.regex.charAt(this.offset) != ')') throw ex("parser.factor.1", this.offset);
this.offset ++;
} else {
if (ch == '?') this.offset --; // Points '('.
this.next();
condition = this.parseFactor();
switch (condition.type) {
case Token.LOOKAHEAD:
case Token.NEGATIVELOOKAHEAD:
case Token.LOOKBEHIND:
case Token.NEGATIVELOOKBEHIND:
break;
case Token.ANCHOR:
if (this.read() != T_RPAREN) throw ex("parser.factor.1", this.offset-1);
break;
default:
throw ex("parser.factor.5", this.offset);
}
}
// Parses yes/no-patterns.
this.next();
Token yesPattern = this.parseRegex();
Token noPattern = null;
if (yesPattern.type == Token.UNION) {
if (yesPattern.size() != 2) throw ex("parser.factor.6", this.offset);
noPattern = yesPattern.getChild(1);
yesPattern = yesPattern.getChild(0);
}
if (this.read() != T_RPAREN) throw ex("parser.factor.1", this.offset-1);
this.next();
return Token.createCondition(refno, condition, yesPattern, noPattern);
}
Token processModifiers() throws ParseException {
// this.offset points the next of '?'.
// modifiers ::= [imsw]* ('-' [imsw]*)? ':'
int add = 0, mask = 0, ch = -1;
while (this.offset < this.regexlen) {
ch = this.regex.charAt(this.offset);
int v = REUtil.getOptionValue(ch);
if (v == 0) break; // '-' or ':'?
add |= v;
this.offset ++;
}
if (this.offset >= this.regexlen) throw ex("parser.factor.2", this.offset-1);
if (ch == '-') {
this.offset ++;
while (this.offset < this.regexlen) {
ch = this.regex.charAt(this.offset);
int v = REUtil.getOptionValue(ch);
if (v == 0) break; // ':'?
mask |= v;
this.offset ++;
}
if (this.offset >= this.regexlen) throw ex("parser.factor.2", this.offset-1);
}
Token tok;
if (ch == ':') {
this.offset ++;
this.next();
tok = Token.createModifierGroup(this.parseRegex(), add, mask);
if (this.read() != T_RPAREN) throw ex("parser.factor.1", this.offset-1);
this.next();
} else if (ch == ')') { // such as (?-i)
this.offset ++;
this.next();
tok = Token.createModifierGroup(this.parseRegex(), add, mask);
} else
throw ex("parser.factor.3", this.offset);
return tok;
}
Token processIndependent() throws ParseException {
this.next();
Token tok = Token.createLook(Token.INDEPENDENT, this.parseRegex());
if (this.read() != T_RPAREN) throw ex("parser.factor.1", this.offset-1);
this.next(); // Skips ')'
return tok;
}
Token processBacksolidus_c() throws ParseException {
int ch2; // Must be in 0x0040-0x005f
if (this.offset >= this.regexlen
|| ((ch2 = this.regex.charAt(this.offset++)) & 0xffe0) != 0x0040)
throw ex("parser.atom.1", this.offset-1);
this.next();
return Token.createChar(ch2-0x40);
}
Token processBacksolidus_C() throws ParseException {
throw ex("parser.process.1", this.offset);
}
Token processBacksolidus_i() throws ParseException {
Token tok = Token.createChar('i');
this.next();
return tok;
}
Token processBacksolidus_I() throws ParseException {
throw ex("parser.process.1", this.offset);
}
Token processBacksolidus_g() throws ParseException {
this.next();
return Token.getGraphemePattern();
}
Token processBacksolidus_X() throws ParseException {
this.next();
return Token.getCombiningCharacterSequence();
}
Token processBackreference() throws ParseException {
int refnum = this.chardata-'0';
Token tok = Token.createBackReference(refnum);
this.hasBackReferences = true;
if (this.references == null) this.references = new Vector();
this.references.addElement(new ReferencePosition(refnum, this.offset-2));
this.next();
return tok;
}
// ----------------------------------------------------------------
/**
* factor ::= ('^' | '$' | '\A' | '\Z' | '\z' | '\b' | '\B' | '\<' | '\>'
* | atom (('*' | '+' | '?' | minmax ) '?'? )?)
* | '(?=' regex ')' | '(?!' regex ')' | '(?<=' regex ')' | '(?<!' regex ')'
* | '(?#' [^)]* ')'
* minmax ::= '{' min (',' max?)? '}'
* min ::= [0-9]+
* max ::= [0-9]+
*/
Token parseFactor() throws ParseException {
int ch = this.read();
Token tok;
switch (ch) {
case T_CARET: return this.processCaret();
case T_DOLLAR: return this.processDollar();
case T_LOOKAHEAD: return this.processLookahead();
case T_NEGATIVELOOKAHEAD: return this.processNegativelookahead();
case T_LOOKBEHIND: return this.processLookbehind();
case T_NEGATIVELOOKBEHIND: return this.processNegativelookbehind();
case T_COMMENT:
this.next();
return Token.createEmpty();
case T_BACKSOLIDUS:
switch (this.chardata) {
case 'A': return this.processBacksolidus_A();
case 'Z': return this.processBacksolidus_Z();
case 'z': return this.processBacksolidus_z();
case 'b': return this.processBacksolidus_b();
case 'B': return this.processBacksolidus_B();
case '<': return this.processBacksolidus_lt();
case '>': return this.processBacksolidus_gt();
}
// through down
}
tok = this.parseAtom();
ch = this.read();
switch (ch) {
case T_STAR: return this.processStar(tok);
case T_PLUS: return this.processPlus(tok);
case T_QUESTION: return this.processQuestion(tok);
case T_CHAR:
if (this.chardata == '{' && this.offset < this.regexlen) {
int off = this.offset; // this.offset -> next of '{'
int min = 0, max = -1;
if ((ch = this.regex.charAt(off++)) >= '0' && ch <= '9') {
min = ch -'0';
while (off < this.regexlen
&& (ch = this.regex.charAt(off++)) >= '0' && ch <= '9') {
min = min*10 +ch-'0';
if (min < 0)
throw ex("parser.quantifier.5", this.offset);
}
}
else {
throw ex("parser.quantifier.1", this.offset);
}
max = min;
if (ch == ',') {
if (off >= this.regexlen) {
throw ex("parser.quantifier.3", this.offset);
}
else if ((ch = this.regex.charAt(off++)) >= '0' && ch <= '9') {
max = ch -'0'; // {min,max}
while (off < this.regexlen
&& (ch = this.regex.charAt(off++)) >= '0'
&& ch <= '9') {
max = max*10 +ch-'0';
if (max < 0)
throw ex("parser.quantifier.5", this.offset);
}
if (min > max)
throw ex("parser.quantifier.4", this.offset);
}
else { // assume {min,}
max = -1;
}
}
if (ch != '}')
throw ex("parser.quantifier.2", this.offset);
if (this.checkQuestion(off)) { // off -> next of '}'
tok = Token.createNGClosure(tok);
this.offset = off+1;
} else {
tok = Token.createClosure(tok);
this.offset = off;
}
tok.setMin(min);
tok.setMax(max);
//System.err.println("CLOSURE: "+min+", "+max);
this.next();
}
}
return tok;
}
/**
* atom ::= char | '.' | char-class | '(' regex ')' | '(?:' regex ')' | '\' [0-9]
* | '\w' | '\W' | '\d' | '\D' | '\s' | '\S' | category-block
* | '(?>' regex ')'
* char ::= '\\' | '\' [efnrt] | bmp-code | character-1
*/
Token parseAtom() throws ParseException {
int ch = this.read();
Token tok = null;
switch (ch) {
case T_LPAREN: return this.processParen();
case T_LPAREN2: return this.processParen2(); // '(?:'
case T_CONDITION: return this.processCondition(); // '(?('
case T_MODIFIERS: return this.processModifiers(); // (?modifiers ... )
case T_INDEPENDENT: return this.processIndependent();
case T_DOT:
this.next(); // Skips '.'
tok = Token.token_dot;
break;
/**
* char-class ::= '[' ( '^'? range ','?)+ ']'
* range ::= '\d' | '\w' | '\s' | category-block | range-char
* | range-char '-' range-char
* range-char ::= '\[' | '\]' | '\\' | '\' [,-efnrtv] | bmp-code | character-2
* bmp-char ::= '\' 'u' [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F]
*/
case T_LBRACKET: return this.parseCharacterClass(true);
case T_SET_OPERATIONS: return this.parseSetOperations();
case T_BACKSOLIDUS:
switch (this.chardata) {
case 'd': case 'D':
case 'w': case 'W':
case 's': case 'S':
tok = this.getTokenForShorthand(this.chardata);
this.next();
return tok;
case 'e': case 'f': case 'n': case 'r':
case 't': case 'u': case 'v': case 'x':
{
int ch2 = this.decodeEscaped();
if (ch2 < 0x10000) {
tok = Token.createChar(ch2);
} else {
tok = Token.createString(REUtil.decomposeToSurrogates(ch2));
}
}
break;
case 'c': return this.processBacksolidus_c();
case 'C': return this.processBacksolidus_C();
case 'i': return this.processBacksolidus_i();
case 'I': return this.processBacksolidus_I();
case 'g': return this.processBacksolidus_g();
case 'X': return this.processBacksolidus_X();
case '1': case '2': case '3': case '4':
case '5': case '6': case '7': case '8': case '9':
return this.processBackreference();
case 'P':
case 'p':
int pstart = this.offset;
tok = processBacksolidus_pP(this.chardata);
if (tok == null) throw this.ex("parser.atom.5", pstart);
break;
default:
tok = Token.createChar(this.chardata);
}
this.next();
break;
case T_CHAR:
if (this.chardata == ']' || this.chardata == '{' || this.chardata == '}')
throw this.ex("parser.atom.4", this.offset-1);
tok = Token.createChar(this.chardata);
int high = this.chardata;
this.next();
if (REUtil.isHighSurrogate(high)
&& this.read() == T_CHAR && REUtil.isLowSurrogate(this.chardata)) {
char[] sur = new char[2];
sur[0] = (char)high;
sur[1] = (char)this.chardata;
tok = Token.createParen(Token.createString(new String(sur)), 0);
this.next();
}
break;
default:
throw this.ex("parser.atom.4", this.offset-1);
}
return tok;
}
protected RangeToken processBacksolidus_pP(int c) throws ParseException {
this.next();
if (this.read() != T_CHAR || this.chardata != '{')
throw this.ex("parser.atom.2", this.offset-1);
// handle category escape
boolean positive = c == 'p';
int namestart = this.offset;
int nameend = this.regex.indexOf('}', namestart);
if (nameend < 0)
throw this.ex("parser.atom.3", this.offset);
String pname = this.regex.substring(namestart, nameend);
this.offset = nameend+1;
return Token.getRange(pname, positive, this.isSet(RegularExpression.XMLSCHEMA_MODE));
}
int processCIinCharacterClass(RangeToken tok, int c) {
return this.decodeEscaped();
}
/**
* char-class ::= '[' ( '^'? range ','?)+ ']'
* range ::= '\d' | '\w' | '\s' | category-block | range-char
* | range-char '-' range-char
* range-char ::= '\[' | '\]' | '\\' | '\' [,-efnrtv] | bmp-code | character-2
* bmp-code ::= '\' 'u' [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F]
*/
protected RangeToken parseCharacterClass(boolean useNrange) throws ParseException {
this.setContext(S_INBRACKETS);
this.next(); // '['
boolean nrange = false;
RangeToken base = null;
RangeToken tok;
if (this.read() == T_CHAR && this.chardata == '^') {
nrange = true;
this.next(); // '^'
if (useNrange) {
tok = Token.createNRange();
} else {
base = Token.createRange();
base.addRange(0, Token.UTF16_MAX);
tok = Token.createRange();
}
} else {
tok = Token.createRange();
}
int type;
boolean firstloop = true;
while ((type = this.read()) != T_EOF) {
if (type == T_CHAR && this.chardata == ']' && !firstloop)
break;
firstloop = false;
int c = this.chardata;
boolean end = false;
if (type == T_BACKSOLIDUS) {
switch (c) {
case 'd': case 'D':
case 'w': case 'W':
case 's': case 'S':
tok.mergeRanges(this.getTokenForShorthand(c));
end = true;
break;
case 'i': case 'I':
case 'c': case 'C':
c = this.processCIinCharacterClass(tok, c);
if (c < 0) end = true;
break;
case 'p':
case 'P':
int pstart = this.offset;
RangeToken tok2 = this.processBacksolidus_pP(c);
if (tok2 == null) throw this.ex("parser.atom.5", pstart);
tok.mergeRanges(tok2);
end = true;
break;
default:
c = this.decodeEscaped();
} // \ + c
} // backsolidus
// POSIX Character class such as [:alnum:]
else if (type == T_POSIX_CHARCLASS_START) {
int nameend = this.regex.indexOf(':', this.offset);
if (nameend < 0) throw this.ex("parser.cc.1", this.offset);
boolean positive = true;
if (this.regex.charAt(this.offset) == '^') {
this.offset ++;
positive = false;
}
String name = this.regex.substring(this.offset, nameend);
RangeToken range = Token.getRange(name, positive,
this.isSet(RegularExpression.XMLSCHEMA_MODE));
if (range == null) throw this.ex("parser.cc.3", this.offset);
tok.mergeRanges(range);
end = true;
if (nameend+1 >= this.regexlen || this.regex.charAt(nameend+1) != ']')
throw this.ex("parser.cc.1", nameend);
this.offset = nameend+2;
}
this.next();
if (!end) { // if not shorthands...
if (this.read() != T_CHAR || this.chardata != '-') { // Here is no '-'.
tok.addRange(c, c);
} else {
this.next(); // Skips '-'
if ((type = this.read()) == T_EOF) throw this.ex("parser.cc.2", this.offset);
if (type == T_CHAR && this.chardata == ']') {
tok.addRange(c, c);
tok.addRange('-', '-');
} else {
int rangeend = this.chardata;
if (type == T_BACKSOLIDUS)
rangeend = this.decodeEscaped();
this.next();
tok.addRange(c, rangeend);
}
}
}
if (this.isSet(RegularExpression.SPECIAL_COMMA)
&& this.read() == T_CHAR && this.chardata == ',')
this.next();
}
if (this.read() == T_EOF)
throw this.ex("parser.cc.2", this.offset);
if (!useNrange && nrange) {
base.subtractRanges(tok);
tok = base;
}
tok.sortRanges();
tok.compactRanges();
//tok.dumpRanges();
/*
if (this.isSet(RegularExpression.IGNORE_CASE))
tok = RangeToken.createCaseInsensitiveToken(tok);
*/
this.setContext(S_NORMAL);
this.next(); // Skips ']'
return tok;
}
/**
* '(?[' ... ']' (('-' | '+' | '&') '[' ... ']')? ')'
*/
protected RangeToken parseSetOperations() throws ParseException {
RangeToken tok = this.parseCharacterClass(false);
int type;
while ((type = this.read()) != T_RPAREN) {
int ch = this.chardata;
if (type == T_CHAR && (ch == '-' || ch == '&')
|| type == T_PLUS) {
this.next();
if (this.read() != T_LBRACKET) throw ex("parser.ope.1", this.offset-1);
RangeToken t2 = this.parseCharacterClass(false);
if (type == T_PLUS)
tok.mergeRanges(t2);
else if (ch == '-')
tok.subtractRanges(t2);
else if (ch == '&')
tok.intersectRanges(t2);
else
throw new RuntimeException("ASSERT");
} else {
throw ex("parser.ope.2", this.offset-1);
}
}
this.next();
return tok;
}
Token getTokenForShorthand(int ch) {
Token tok;
switch (ch) {
case 'd':
tok = this.isSet(RegularExpression.USE_UNICODE_CATEGORY)
? Token.getRange("Nd", true) : Token.token_0to9;
break;
case 'D':
tok = this.isSet(RegularExpression.USE_UNICODE_CATEGORY)
? Token.getRange("Nd", false) : Token.token_not_0to9;
break;
case 'w':
tok = this.isSet(RegularExpression.USE_UNICODE_CATEGORY)
? Token.getRange("IsWord", true) : Token.token_wordchars;
break;
case 'W':
tok = this.isSet(RegularExpression.USE_UNICODE_CATEGORY)
? Token.getRange("IsWord", false) : Token.token_not_wordchars;
break;
case 's':
tok = this.isSet(RegularExpression.USE_UNICODE_CATEGORY)
? Token.getRange("IsSpace", true) : Token.token_spaces;
break;
case 'S':
tok = this.isSet(RegularExpression.USE_UNICODE_CATEGORY)
? Token.getRange("IsSpace", false) : Token.token_not_spaces;
break;
default:
throw new RuntimeException("Internal Error: shorthands: \\u"+Integer.toString(ch, 16));
}
return tok;
}
/**
*/
int decodeEscaped() throws ParseException {
if (this.read() != T_BACKSOLIDUS) throw ex("parser.next.1", this.offset-1);
int c = this.chardata;
switch (c) {
case 'e': c = 0x1b; break; // ESCAPE U+001B
case 'f': c = '\f'; break; // FORM FEED U+000C
case 'n': c = '\n'; break; // LINE FEED U+000A
case 'r': c = '\r'; break; // CRRIAGE RETURN U+000D
case 't': c = '\t'; break; // HORIZONTAL TABULATION U+0009
//case 'v': c = 0x0b; break; // VERTICAL TABULATION U+000B
case 'x':
this.next();
if (this.read() != T_CHAR) throw ex("parser.descape.1", this.offset-1);
if (this.chardata == '{') {
int v1 = 0;
int uv = 0;
do {
this.next();
if (this.read() != T_CHAR) throw ex("parser.descape.1", this.offset-1);
if ((v1 = hexChar(this.chardata)) < 0)
break;
if (uv > uv*16) throw ex("parser.descape.2", this.offset-1);
uv = uv*16+v1;
} while (true);
if (this.chardata != '}') throw ex("parser.descape.3", this.offset-1);
if (uv > Token.UTF16_MAX) throw ex("parser.descape.4", this.offset-1);
c = uv;
} else {
int v1 = 0;
if (this.read() != T_CHAR || (v1 = hexChar(this.chardata)) < 0)
throw ex("parser.descape.1", this.offset-1);
int uv = v1;
this.next();
if (this.read() != T_CHAR || (v1 = hexChar(this.chardata)) < 0)
throw ex("parser.descape.1", this.offset-1);
uv = uv*16+v1;
c = uv;
}
break;
case 'u':
int v1 = 0;
this.next();
if (this.read() != T_CHAR || (v1 = hexChar(this.chardata)) < 0)
throw ex("parser.descape.1", this.offset-1);
int uv = v1;
this.next();
if (this.read() != T_CHAR || (v1 = hexChar(this.chardata)) < 0)
throw ex("parser.descape.1", this.offset-1);
uv = uv*16+v1;
this.next();
if (this.read() != T_CHAR || (v1 = hexChar(this.chardata)) < 0)
throw ex("parser.descape.1", this.offset-1);
uv = uv*16+v1;
this.next();
if (this.read() != T_CHAR || (v1 = hexChar(this.chardata)) < 0)
throw ex("parser.descape.1", this.offset-1);
uv = uv*16+v1;
c = uv;
break;
case 'v':
this.next();
if (this.read() != T_CHAR || (v1 = hexChar(this.chardata)) < 0)
throw ex("parser.descape.1", this.offset-1);
uv = v1;
this.next();
if (this.read() != T_CHAR || (v1 = hexChar(this.chardata)) < 0)
throw ex("parser.descape.1", this.offset-1);
uv = uv*16+v1;
this.next();
if (this.read() != T_CHAR || (v1 = hexChar(this.chardata)) < 0)
throw ex("parser.descape.1", this.offset-1);
uv = uv*16+v1;
this.next();
if (this.read() != T_CHAR || (v1 = hexChar(this.chardata)) < 0)
throw ex("parser.descape.1", this.offset-1);
uv = uv*16+v1;
this.next();
if (this.read() != T_CHAR || (v1 = hexChar(this.chardata)) < 0)
throw ex("parser.descape.1", this.offset-1);
uv = uv*16+v1;
this.next();
if (this.read() != T_CHAR || (v1 = hexChar(this.chardata)) < 0)
throw ex("parser.descape.1", this.offset-1);
uv = uv*16+v1;
if (uv > Token.UTF16_MAX) throw ex("parser.descappe.4", this.offset-1);
c = uv;
break;
case 'A':
case 'Z':
case 'z':
throw ex("parser.descape.5", this.offset-2);
default:
}
return c;
}
static private final int hexChar(int ch) {
if (ch < '0') return -1;
if (ch > 'f') return -1;
if (ch <= '9') return ch-'0';
if (ch < 'A') return -1;
if (ch <= 'F') return ch-'A'+10;
if (ch < 'a') return -1;
return ch-'a'+10;
}
}
msv-2009.1/xsdlib/src-apache/com/sun/msv/datatype/regexp/ParseException.java 0000644 0001750 0001750 00000006355 10223107437 027214 0 ustar giovanni giovanni /*
* The Apache Software License, Version 1.1
*
*
* Copyright (c) 1999-2002 The Apache Software Foundation. All rights
* reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
*
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
*
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in
* the documentation and/or other materials provided with the
* distribution.
*
* 3. The end-user documentation included with the redistribution,
* if any, must include the following acknowledgment:
* "This product includes software developed by the
* Apache Software Foundation (http://www.apache.org/)."
* Alternately, this acknowledgment may appear in the software itself,
* if and wherever such third-party acknowledgments normally appear.
*
* 4. The names "Xerces" and "Apache Software Foundation" must
* not be used to endorse or promote products derived from this
* software without prior written permission. For written
* permission, please contact apache@apache.org.
*
* 5. Products derived from this software may not be called "Apache",
* nor may "Apache" appear in their name, without prior written
* permission of the Apache Software Foundation.
*
* THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESSED OR IMPLIED
* WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
* OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
* DISCLAIMED. IN NO EVENT SHALL THE APACHE SOFTWARE FOUNDATION OR
* ITS CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
* SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
* LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF
* USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
* ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
* OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT
* OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
* SUCH DAMAGE.
* ====================================================================
*
* This software consists of voluntary contributions made by many
* individuals on behalf of the Apache Software Foundation and was
* originally based on software copyright (c) 1999, International
* Business Machines, Inc., http://www.apache.org. For more
* information on the Apache Software Foundation, please see
* .
*/
package com.sun.msv.datatype.regexp;
/**
*
* @author TAMURA Kent <kent@trl.ibm.co.jp>
* @version ParseException.java,v 1.3 2002/08/09 15:18:17 neilg Exp
*/
class ParseException extends RuntimeException {
int location;
/*
public ParseException(String mes) {
this(mes, -1);
}
*/
/**
*
*/
public ParseException(String mes, int location) {
super(mes);
this.location = location;
}
/**
*
* @return -1 if location information is not available.
*/
public int getLocation() {
return this.location;
}
}
msv-2009.1/xsdlib/src-apache/com/sun/msv/datatype/regexp/message.properties 0000644 0001750 0001750 00000004207 10223107437 027154 0 ustar giovanni giovanni parser.parse.1=Wrong character.
parser.parse.2=Invalid reference number.
parser.next.1=A character is required after \\.
parser.next.2='?' is not expected. '(?:' or '(?=' or '(?!' or '(?<' or '(?#' or '(?>'?
parser.next.3='(?<=' or '(?.
*/
package com.sun.msv.datatype.regexp;
import java.util.Hashtable;
import java.util.Vector;
/**
* This class represents a node in parse tree.
*
* @version Token.java,v 1.7 2003/02/25 14:43:13 sandygao Exp
*/
class Token implements java.io.Serializable {
static final boolean COUNTTOKENS = true;
static int tokens = 0;
static final int CHAR = 0; // Literal char
static final int DOT = 11; // .
static final int CONCAT = 1; // XY
static final int UNION = 2; // X|Y|Z
static final int CLOSURE = 3; // X*
static final int RANGE = 4; // [a-zA-Z] etc.
static final int NRANGE = 5; // [^a-zA-Z] etc.
static final int PAREN = 6; // (X) or (?:X)
static final int EMPTY = 7; //
static final int ANCHOR = 8; // ^ $ \b \B \< \> \A \Z \z
static final int NONGREEDYCLOSURE = 9; // *? +?
static final int STRING = 10; // strings
static final int BACKREFERENCE = 12; // back references
static final int LOOKAHEAD = 20; // (?=...)
static final int NEGATIVELOOKAHEAD = 21; // (?!...)
static final int LOOKBEHIND = 22; // (?<=...)
static final int NEGATIVELOOKBEHIND = 23; // (?...)
static final int MODIFIERGROUP = 25; // (?ims-ims:...)
static final int CONDITION = 26; // (?(...)yes|no)
static final int UTF16_MAX = 0x10ffff;
int type;
static Token token_dot;
static Token token_0to9;
static Token token_wordchars;
static Token token_not_0to9;
static Token token_not_wordchars;
static Token token_spaces;
static Token token_not_spaces;
static Token token_empty;
static Token token_linebeginning;
static Token token_linebeginning2;
static Token token_lineend;
static Token token_stringbeginning;
static Token token_stringend;
static Token token_stringend2;
static Token token_wordedge;
static Token token_not_wordedge;
static Token token_wordbeginning;
static Token token_wordend;
static {
Token.token_empty = new Token(Token.EMPTY);
Token.token_linebeginning = Token.createAnchor('^');
Token.token_linebeginning2 = Token.createAnchor('@');
Token.token_lineend = Token.createAnchor('$');
Token.token_stringbeginning = Token.createAnchor('A');
Token.token_stringend = Token.createAnchor('z');
Token.token_stringend2 = Token.createAnchor('Z');
Token.token_wordedge = Token.createAnchor('b');
Token.token_not_wordedge = Token.createAnchor('B');
Token.token_wordbeginning = Token.createAnchor('<');
Token.token_wordend = Token.createAnchor('>');
Token.token_dot = new Token(Token.DOT);
Token.token_0to9 = Token.createRange();
Token.token_0to9.addRange('0', '9');
Token.token_wordchars = Token.createRange();
Token.token_wordchars.addRange('0', '9');
Token.token_wordchars.addRange('A', 'Z');
Token.token_wordchars.addRange('_', '_');
Token.token_wordchars.addRange('a', 'z');
Token.token_spaces = Token.createRange();
Token.token_spaces.addRange('\t', '\t');
Token.token_spaces.addRange('\n', '\n');
Token.token_spaces.addRange('\f', '\f');
Token.token_spaces.addRange('\r', '\r');
Token.token_spaces.addRange(' ', ' ');
Token.token_not_0to9 = Token.complementRanges(Token.token_0to9);
Token.token_not_wordchars = Token.complementRanges(Token.token_wordchars);
Token.token_not_spaces = Token.complementRanges(Token.token_spaces);
}
static Token.ParenToken createLook(int type, Token child) {
if (COUNTTOKENS) Token.tokens ++;
return new Token.ParenToken(type, child, 0);
}
static Token.ParenToken createParen(Token child, int pnumber) {
if (COUNTTOKENS) Token.tokens ++;
return new Token.ParenToken(Token.PAREN, child, pnumber);
}
static Token.ClosureToken createClosure(Token tok) {
if (COUNTTOKENS) Token.tokens ++;
return new Token.ClosureToken(Token.CLOSURE, tok);
}
static Token.ClosureToken createNGClosure(Token tok) {
if (COUNTTOKENS) Token.tokens ++;
return new Token.ClosureToken(Token.NONGREEDYCLOSURE, tok);
}
static Token.ConcatToken createConcat(Token tok1, Token tok2) {
if (COUNTTOKENS) Token.tokens ++;
return new Token.ConcatToken(tok1, tok2);
}
static Token.UnionToken createConcat() {
if (COUNTTOKENS) Token.tokens ++;
return new Token.UnionToken(Token.CONCAT); // *** It is not a bug.
}
static Token.UnionToken createUnion() {
if (COUNTTOKENS) Token.tokens ++;
return new Token.UnionToken(Token.UNION);
}
static Token createEmpty() {
return Token.token_empty;
}
static RangeToken createRange() {
if (COUNTTOKENS) Token.tokens ++;
return new RangeToken(Token.RANGE);
}
static RangeToken createNRange() {
if (COUNTTOKENS) Token.tokens ++;
return new RangeToken(Token.NRANGE);
}
static Token.CharToken createChar(int ch) {
if (COUNTTOKENS) Token.tokens ++;
return new Token.CharToken(Token.CHAR, ch);
}
static private Token.CharToken createAnchor(int ch) {
if (COUNTTOKENS) Token.tokens ++;
return new Token.CharToken(Token.ANCHOR, ch);
}
static Token.StringToken createBackReference(int refno) {
if (COUNTTOKENS) Token.tokens ++;
return new Token.StringToken(Token.BACKREFERENCE, null, refno);
}
static Token.StringToken createString(String str) {
if (COUNTTOKENS) Token.tokens ++;
return new Token.StringToken(Token.STRING, str, 0);
}
static Token.ModifierToken createModifierGroup(Token child, int add, int mask) {
if (COUNTTOKENS) Token.tokens ++;
return new Token.ModifierToken(child, add, mask);
}
static Token.ConditionToken createCondition(int refno, Token condition,
Token yespat, Token nopat) {
if (COUNTTOKENS) Token.tokens ++;
return new Token.ConditionToken(refno, condition, yespat, nopat);
}
protected Token(int type) {
this.type = type;
}
/**
* A number of children.
*/
int size() {
return 0;
}
Token getChild(int index) {
return null;
}
void addChild(Token tok) {
throw new RuntimeException("Not supported.");
}
// for RANGE or NRANGE
protected void addRange(int start, int end) {
throw new RuntimeException("Not supported.");
}
protected void sortRanges() {
throw new RuntimeException("Not supported.");
}
protected void compactRanges() {
throw new RuntimeException("Not supported.");
}
protected void mergeRanges(Token tok) {
throw new RuntimeException("Not supported.");
}
protected void subtractRanges(Token tok) {
throw new RuntimeException("Not supported.");
}
protected void intersectRanges(Token tok) {
throw new RuntimeException("Not supported.");
}
static Token complementRanges(Token tok) {
return RangeToken.complementRanges(tok);
}
void setMin(int min) { // for CLOSURE
}
void setMax(int max) { // for CLOSURE
}
int getMin() { // for CLOSURE
return -1;
}
int getMax() { // for CLOSURE
return -1;
}
int getReferenceNumber() { // for STRING
return 0;
}
String getString() { // for STRING
return null;
}
int getParenNumber() {
return 0;
}
int getChar() {
return -1;
}
public String toString() {
return this.toString(0);
}
public String toString(int options) {
return this.type == Token.DOT ? "." : "";
}
/**
* How many characters are needed?
*/
final int getMinLength() {
switch (this.type) {
case CONCAT:
int sum = 0;
for (int i = 0; i < this.size(); i ++)
sum += this.getChild(i).getMinLength();
return sum;
case CONDITION:
case UNION:
if (this.size() == 0)
return 0;
int ret = this.getChild(0).getMinLength();
for (int i = 1; i < this.size(); i ++) {
int min = this.getChild(i).getMinLength();
if (min < ret) ret = min;
}
return ret;
case CLOSURE:
case NONGREEDYCLOSURE:
if (this.getMin() >= 0)
return this.getMin() * this.getChild(0).getMinLength();
return 0;
case EMPTY:
case ANCHOR:
return 0;
case DOT:
case CHAR:
case RANGE:
case NRANGE:
return 1;
case INDEPENDENT:
case PAREN:
case MODIFIERGROUP:
return this.getChild(0).getMinLength();
case BACKREFERENCE:
return 0; // *******
case STRING:
return this.getString().length();
case LOOKAHEAD:
case NEGATIVELOOKAHEAD:
case LOOKBEHIND:
case NEGATIVELOOKBEHIND:
return 0; // ***** Really?
default:
throw new RuntimeException("Token#getMinLength(): Invalid Type: "+this.type);
}
}
final int getMaxLength() {
switch (this.type) {
case CONCAT:
int sum = 0;
for (int i = 0; i < this.size(); i ++) {
int d = this.getChild(i).getMaxLength();
if (d < 0) return -1;
sum += d;
}
return sum;
case CONDITION:
case UNION:
if (this.size() == 0)
return 0;
int ret = this.getChild(0).getMaxLength();
for (int i = 1; ret >= 0 && i < this.size(); i ++) {
int max = this.getChild(i).getMaxLength();
if (max < 0) { // infinity
ret = -1;
break;
}
if (max > ret) ret = max;
}
return ret;
case CLOSURE:
case NONGREEDYCLOSURE:
if (this.getMax() >= 0)
// When this.child.getMaxLength() < 0,
// this returns minus value
return this.getMax() * this.getChild(0).getMaxLength();
return -1;
case EMPTY:
case ANCHOR:
return 0;
case CHAR:
return 1;
case DOT:
case RANGE:
case NRANGE:
return 2;
case INDEPENDENT:
case PAREN:
case MODIFIERGROUP:
return this.getChild(0).getMaxLength();
case BACKREFERENCE:
return -1; // ******
case STRING:
return this.getString().length();
case LOOKAHEAD:
case NEGATIVELOOKAHEAD:
case LOOKBEHIND:
case NEGATIVELOOKBEHIND:
return 0; // ***** Really?
default:
throw new RuntimeException("Token#getMaxLength(): Invalid Type: "+this.type);
}
}
static final int FC_CONTINUE = 0;
static final int FC_TERMINAL = 1;
static final int FC_ANY = 2;
private static final boolean isSet(int options, int flag) {
return (options & flag) == flag;
}
final int analyzeFirstCharacter(RangeToken result, int options) {
switch (this.type) {
case CONCAT:
int ret = FC_CONTINUE;
for (int i = 0; i < this.size(); i ++)
if ((ret = this.getChild(i).analyzeFirstCharacter(result, options)) != FC_CONTINUE)
break;
return ret;
case UNION:
if (this.size() == 0)
return FC_CONTINUE;
/*
* a|b|c -> FC_TERMINAL
* a|.|c -> FC_ANY
* a|b| -> FC_CONTINUE
*/
int ret2 = FC_CONTINUE;
boolean hasEmpty = false;
for (int i = 0; i < this.size(); i ++) {
ret2 = this.getChild(i).analyzeFirstCharacter(result, options);
if (ret2 == FC_ANY)
break;
else if (ret2 == FC_CONTINUE)
hasEmpty = true;
}
return hasEmpty ? FC_CONTINUE : ret2;
case CONDITION:
int ret3 = this.getChild(0).analyzeFirstCharacter(result, options);
if (this.size() == 1) return FC_CONTINUE;
if (ret3 == FC_ANY) return ret3;
int ret4 = this.getChild(1).analyzeFirstCharacter(result, options);
if (ret4 == FC_ANY) return ret4;
return ret3 == FC_CONTINUE || ret4 == FC_CONTINUE ? FC_CONTINUE : FC_TERMINAL;
case CLOSURE:
case NONGREEDYCLOSURE:
this.getChild(0).analyzeFirstCharacter(result, options);
return FC_CONTINUE;
case EMPTY:
case ANCHOR:
return FC_CONTINUE;
case CHAR:
int ch = this.getChar();
result.addRange(ch, ch);
if (ch < 0x10000 && isSet(options, RegularExpression.IGNORE_CASE)) {
ch = Character.toUpperCase((char)ch);
result.addRange(ch, ch);
ch = Character.toLowerCase((char)ch);
result.addRange(ch, ch);
}
return FC_TERMINAL;
case DOT: // ****
if (isSet(options, RegularExpression.SINGLE_LINE)) {
return FC_CONTINUE; // **** We can not optimize.
} else {
return FC_CONTINUE;
/*
result.addRange(0, RegularExpression.LINE_FEED-1);
result.addRange(RegularExpression.LINE_FEED+1, RegularExpression.CARRIAGE_RETURN-1);
result.addRange(RegularExpression.CARRIAGE_RETURN+1,
RegularExpression.LINE_SEPARATOR-1);
result.addRange(RegularExpression.PARAGRAPH_SEPARATOR+1, UTF16_MAX);
return 1;
*/
}
case RANGE:
if (isSet(options, RegularExpression.IGNORE_CASE)) {
result.mergeRanges(((RangeToken)this).getCaseInsensitiveToken());
} else {
result.mergeRanges(this);
}
return FC_TERMINAL;
case NRANGE: // ****
if (isSet(options, RegularExpression.IGNORE_CASE)) {
result.mergeRanges(Token.complementRanges(((RangeToken)this).getCaseInsensitiveToken()));
} else {
result.mergeRanges(Token.complementRanges(this));
}
return FC_TERMINAL;
case INDEPENDENT:
case PAREN:
return this.getChild(0).analyzeFirstCharacter(result, options);
case MODIFIERGROUP:
options |= ((ModifierToken)this).getOptions();
options &= ~((ModifierToken)this).getOptionsMask();
return this.getChild(0).analyzeFirstCharacter(result, options);
case BACKREFERENCE:
result.addRange(0, UTF16_MAX); // **** We can not optimize.
return FC_ANY;
case STRING:
int cha = this.getString().charAt(0);
int ch2;
if (REUtil.isHighSurrogate(cha)
&& this.getString().length() >= 2
&& REUtil.isLowSurrogate((ch2 = this.getString().charAt(1))))
cha = REUtil.composeFromSurrogates(cha, ch2);
result.addRange(cha, cha);
if (cha < 0x10000 && isSet(options, RegularExpression.IGNORE_CASE)) {
cha = Character.toUpperCase((char)cha);
result.addRange(cha, cha);
cha = Character.toLowerCase((char)cha);
result.addRange(cha, cha);
}
return FC_TERMINAL;
case LOOKAHEAD:
case NEGATIVELOOKAHEAD:
case LOOKBEHIND:
case NEGATIVELOOKBEHIND:
return FC_CONTINUE;
default:
throw new RuntimeException("Token#analyzeHeadCharacter(): Invalid Type: "+this.type);
}
}
private final boolean isShorterThan(Token tok) {
if (tok == null) return false;
/*
int mylength;
if (this.type == STRING) mylength = this.getString().length();
else if (this.type == CHAR) mylength = this.getChar() >= 0x10000 ? 2 : 1;
else throw new RuntimeException("Internal Error: Illegal type: "+this.type);
int otherlength;
if (tok.type == STRING) otherlength = tok.getString().length();
else if (tok.type == CHAR) otherlength = tok.getChar() >= 0x10000 ? 2 : 1;
else throw new RuntimeException("Internal Error: Illegal type: "+tok.type);
*/
int mylength;
if (this.type == STRING) mylength = this.getString().length();
else throw new RuntimeException("Internal Error: Illegal type: "+this.type);
int otherlength;
if (tok.type == STRING) otherlength = tok.getString().length();
else throw new RuntimeException("Internal Error: Illegal type: "+tok.type);
return mylength < otherlength;
}
static class FixedStringContainer {
Token token = null;
int options = 0;
FixedStringContainer() {
}
}
final void findFixedString(FixedStringContainer container, int options) {
switch (this.type) {
case CONCAT:
Token prevToken = null;
int prevOptions = 0;
for (int i = 0; i < this.size(); i ++) {
this.getChild(i).findFixedString(container, options);
if (prevToken == null || prevToken.isShorterThan(container.token)) {
prevToken = container.token;
prevOptions = container.options;
}
}
container.token = prevToken;
container.options = prevOptions;
return;
case UNION:
case CLOSURE:
case NONGREEDYCLOSURE:
case EMPTY:
case ANCHOR:
case RANGE:
case DOT:
case NRANGE:
case BACKREFERENCE:
case LOOKAHEAD:
case NEGATIVELOOKAHEAD:
case LOOKBEHIND:
case NEGATIVELOOKBEHIND:
case CONDITION:
container.token = null;
return;
case CHAR: // Ignore CHAR tokens.
container.token = null; // **
return; // **
case STRING:
container.token = this;
container.options = options;
return;
case INDEPENDENT:
case PAREN:
this.getChild(0).findFixedString(container, options);
return;
case MODIFIERGROUP:
options |= ((ModifierToken)this).getOptions();
options &= ~((ModifierToken)this).getOptionsMask();
this.getChild(0).findFixedString(container, options);
return;
default:
throw new RuntimeException("Token#findFixedString(): Invalid Type: "+this.type);
}
}
boolean match(int ch) {
throw new RuntimeException("NFAArrow#match(): Internal error: "+this.type);
}
// ------------------------------------------------------
private final static Hashtable categories = new Hashtable();
private final static Hashtable categories2 = new Hashtable();
private static final String[] categoryNames = {
"Cn", "Lu", "Ll", "Lt", "Lm", "Lo", "Mn", "Me", "Mc", "Nd",
"Nl", "No", "Zs", "Zl", "Zp", "Cc", "Cf", null, "Co", "Cs",
"Pd", "Ps", "Pe", "Pc", "Po", "Sm", "Sc", "Sk", "So", // 28
"Pi", "Pf", // 29, 30
"L", "M", "N", "Z", "C", "P", "S", // 31-37
};
// Schema Rec. {Datatypes} - Punctuation
static final int CHAR_INIT_QUOTE = 29; // Pi - initial quote
static final int CHAR_FINAL_QUOTE = 30; // Pf - final quote
static final int CHAR_LETTER = 31;
static final int CHAR_MARK = 32;
static final int CHAR_NUMBER = 33;
static final int CHAR_SEPARATOR = 34;
static final int CHAR_OTHER = 35;
static final int CHAR_PUNCTUATION = 36;
static final int CHAR_SYMBOL = 37;
//blockNames in UNICODE 3.1 that supported by XML Schema REC
private static final String[] blockNames = {
/*0000..007F;*/ "Basic Latin",
/*0080..00FF;*/ "Latin-1 Supplement",
/*0100..017F;*/ "Latin Extended-A",
/*0180..024F;*/ "Latin Extended-B",
/*0250..02AF;*/ "IPA Extensions",
/*02B0..02FF;*/ "Spacing Modifier Letters",
/*0300..036F;*/ "Combining Diacritical Marks",
/*0370..03FF;*/ "Greek",
/*0400..04FF;*/ "Cyrillic",
/*0530..058F;*/ "Armenian",
/*0590..05FF;*/ "Hebrew",
/*0600..06FF;*/ "Arabic",
/*0700..074F;*/ "Syriac",
/*0780..07BF;*/ "Thaana",
/*0900..097F;*/ "Devanagari",
/*0980..09FF;*/ "Bengali",
/*0A00..0A7F;*/ "Gurmukhi",
/*0A80..0AFF;*/ "Gujarati",
/*0B00..0B7F;*/ "Oriya",
/*0B80..0BFF;*/ "Tamil",
/*0C00..0C7F;*/ "Telugu",
/*0C80..0CFF;*/ "Kannada",
/*0D00..0D7F;*/ "Malayalam",
/*0D80..0DFF;*/ "Sinhala",
/*0E00..0E7F;*/ "Thai",
/*0E80..0EFF;*/ "Lao",
/*0F00..0FFF;*/ "Tibetan",
/*1000..109F;*/ "Myanmar",
/*10A0..10FF;*/ "Georgian",
/*1100..11FF;*/ "Hangul Jamo",
/*1200..137F;*/ "Ethiopic",
/*13A0..13FF;*/ "Cherokee",
/*1400..167F;*/ "Unified Canadian Aboriginal Syllabics",
/*1680..169F;*/ "Ogham",
/*16A0..16FF;*/ "Runic",
/*1780..17FF;*/ "Khmer",
/*1800..18AF;*/ "Mongolian",
/*1E00..1EFF;*/ "Latin Extended Additional",
/*1F00..1FFF;*/ "Greek Extended",
/*2000..206F;*/ "General Punctuation",
/*2070..209F;*/ "Superscripts and Subscripts",
/*20A0..20CF;*/ "Currency Symbols",
/*20D0..20FF;*/ "Combining Marks for Symbols",
/*2100..214F;*/ "Letterlike Symbols",
/*2150..218F;*/ "Number Forms",
/*2190..21FF;*/ "Arrows",
/*2200..22FF;*/ "Mathematical Operators",
/*2300..23FF;*/ "Miscellaneous Technical",
/*2400..243F;*/ "Control Pictures",
/*2440..245F;*/ "Optical Character Recognition",
/*2460..24FF;*/ "Enclosed Alphanumerics",
/*2500..257F;*/ "Box Drawing",
/*2580..259F;*/ "Block Elements",
/*25A0..25FF;*/ "Geometric Shapes",
/*2600..26FF;*/ "Miscellaneous Symbols",
/*2700..27BF;*/ "Dingbats",
/*2800..28FF;*/ "Braille Patterns",
/*2E80..2EFF;*/ "CJK Radicals Supplement",
/*2F00..2FDF;*/ "Kangxi Radicals",
/*2FF0..2FFF;*/ "Ideographic Description Characters",
/*3000..303F;*/ "CJK Symbols and Punctuation",
/*3040..309F;*/ "Hiragana",
/*30A0..30FF;*/ "Katakana",
/*3100..312F;*/ "Bopomofo",
/*3130..318F;*/ "Hangul Compatibility Jamo",
/*3190..319F;*/ "Kanbun",
/*31A0..31BF;*/ "Bopomofo Extended",
/*3200..32FF;*/ "Enclosed CJK Letters and Months",
/*3300..33FF;*/ "CJK Compatibility",
/*3400..4DB5;*/ "CJK Unified Ideographs Extension A",
/*4E00..9FFF;*/ "CJK Unified Ideographs",
/*A000..A48F;*/ "Yi Syllables",
/*A490..A4CF;*/ "Yi Radicals",
/*AC00..D7A3;*/ "Hangul Syllables",
/*E000..F8FF;*/ "Private Use",
/*F900..FAFF;*/ "CJK Compatibility Ideographs",
/*FB00..FB4F;*/ "Alphabetic Presentation Forms",
/*FB50..FDFF;*/ "Arabic Presentation Forms-A",
/*FE20..FE2F;*/ "Combining Half Marks",
/*FE30..FE4F;*/ "CJK Compatibility Forms",
/*FE50..FE6F;*/ "Small Form Variants",
/*FE70..FEFE;*/ "Arabic Presentation Forms-B",
/*FEFF..FEFF;*/ "Specials",
/*FF00..FFEF;*/ "Halfwidth and Fullwidth Forms",
//missing Specials add manually
/*10300..1032F;*/ "Old Italic", // 84
/*10330..1034F;*/ "Gothic",
/*10400..1044F;*/ "Deseret",
/*1D000..1D0FF;*/ "Byzantine Musical Symbols",
/*1D100..1D1FF;*/ "Musical Symbols",
/*1D400..1D7FF;*/ "Mathematical Alphanumeric Symbols",
/*20000..2A6D6;*/ "CJK Unified Ideographs Extension B",
/*2F800..2FA1F;*/ "CJK Compatibility Ideographs Supplement",
/*E0000..E007F;*/ "Tags",
//missing 2 private use add manually
};
//ADD THOSE MANUALLY
//F0000..FFFFD; "Private Use",
//100000..10FFFD; "Private Use"
//FFF0..FFFD; "Specials",
static final String blockRanges =
"\u0000\u007F\u0080\u00FF\u0100\u017F\u0180\u024F\u0250\u02AF\u02B0\u02FF\u0300\u036F"
+"\u0370\u03FF\u0400\u04FF\u0530\u058F\u0590\u05FF\u0600\u06FF\u0700\u074F\u0780\u07BF"
+"\u0900\u097F\u0980\u09FF\u0A00\u0A7F\u0A80\u0AFF\u0B00\u0B7F\u0B80\u0BFF\u0C00\u0C7F\u0C80\u0CFF"
+"\u0D00\u0D7F\u0D80\u0DFF\u0E00\u0E7F\u0E80\u0EFF\u0F00\u0FFF\u1000\u109F\u10A0\u10FF\u1100\u11FF"
+"\u1200\u137F\u13A0\u13FF\u1400\u167F\u1680\u169F\u16A0\u16FF\u1780\u17FF\u1800\u18AF\u1E00\u1EFF"
+"\u1F00\u1FFF\u2000\u206F\u2070\u209F\u20A0\u20CF\u20D0\u20FF\u2100\u214F\u2150\u218F\u2190\u21FF\u2200\u22FF"
+"\u2300\u23FF\u2400\u243F\u2440\u245F\u2460\u24FF\u2500\u257F\u2580\u259F\u25A0\u25FF\u2600\u26FF\u2700\u27BF"
+"\u2800\u28FF\u2E80\u2EFF\u2F00\u2FDF\u2FF0\u2FFF\u3000\u303F\u3040\u309F\u30A0\u30FF\u3100\u312F\u3130\u318F"
+"\u3190\u319F\u31A0\u31BF\u3200\u32FF\u3300\u33FF\u3400\u4DB5\u4E00\u9FFF\uA000\uA48F\uA490\uA4CF"
+"\uAC00\uD7A3\uE000\uF8FF\uF900\uFAFF\uFB00\uFB4F\uFB50\uFDFF"
+"\uFE20\uFE2F\uFE30\uFE4F\uFE50\uFE6F\uFE70\uFEFE\uFEFF\uFEFF\uFF00\uFFEF";
static final int[] nonBMPBlockRanges = {
0x10300, 0x1032F, // 84
0x10330, 0x1034F,
0x10400, 0x1044F,
0x1D000, 0x1D0FF,
0x1D100, 0x1D1FF,
0x1D400, 0x1D7FF,
0x20000, 0x2A6D6,
0x2F800, 0x2FA1F,
0xE0000, 0xE007F
};
private static final int NONBMP_BLOCK_START = 84;
static protected RangeToken getRange(String name, boolean positive) {
if (Token.categories.size() == 0) {
synchronized (Token.categories) {
Token[] ranges = new Token[Token.categoryNames.length];
for (int i = 0; i < ranges.length; i ++) {
ranges[i] = Token.createRange();
}
int type;
for (int i = 0; i < 0x10000; i ++) {
type = Character.getType((char)i);
if (type == Character.START_PUNCTUATION ||
type == Character.END_PUNCTUATION) {
//build table of Pi values
if (i == 0x00AB || i == 0x2018 || i == 0x201B || i == 0x201C ||
i == 0x201F || i == 0x2039) {
type = CHAR_INIT_QUOTE;
}
//build table of Pf values
if (i == 0x00BB || i == 0x2019 || i == 0x201D || i == 0x203A ) {
type = CHAR_FINAL_QUOTE;
}
}
ranges[type].addRange(i, i);
switch (type) {
case Character.UPPERCASE_LETTER:
case Character.LOWERCASE_LETTER:
case Character.TITLECASE_LETTER:
case Character.MODIFIER_LETTER:
case Character.OTHER_LETTER:
type = CHAR_LETTER;
break;
case Character.NON_SPACING_MARK:
case Character.COMBINING_SPACING_MARK:
case Character.ENCLOSING_MARK:
type = CHAR_MARK;
break;
case Character.DECIMAL_DIGIT_NUMBER:
case Character.LETTER_NUMBER:
case Character.OTHER_NUMBER:
type = CHAR_NUMBER;
break;
case Character.SPACE_SEPARATOR:
case Character.LINE_SEPARATOR:
case Character.PARAGRAPH_SEPARATOR:
type = CHAR_SEPARATOR;
break;
case Character.CONTROL:
case Character.FORMAT:
case Character.SURROGATE:
case Character.PRIVATE_USE:
case Character.UNASSIGNED:
type = CHAR_OTHER;
break;
case Character.CONNECTOR_PUNCTUATION:
case Character.DASH_PUNCTUATION:
case Character.START_PUNCTUATION:
case Character.END_PUNCTUATION:
case CHAR_INIT_QUOTE:
case CHAR_FINAL_QUOTE:
case Character.OTHER_PUNCTUATION:
type = CHAR_PUNCTUATION;
break;
case Character.MATH_SYMBOL:
case Character.CURRENCY_SYMBOL:
case Character.MODIFIER_SYMBOL:
case Character.OTHER_SYMBOL:
type = CHAR_SYMBOL;
break;
default:
throw new RuntimeException("org.apache.xerces.utils.regex.Token#getRange(): Unknown Unicode category: "+type);
}
ranges[type].addRange(i, i);
} // for all characters
ranges[Character.UNASSIGNED].addRange(0x10000, Token.UTF16_MAX);
for (int i = 0; i < ranges.length; i ++) {
if (Token.categoryNames[i] != null) {
if (i == Character.UNASSIGNED) { // Unassigned
ranges[i].addRange(0x10000, Token.UTF16_MAX);
}
Token.categories.put(Token.categoryNames[i], ranges[i]);
Token.categories2.put(Token.categoryNames[i],
Token.complementRanges(ranges[i]));
}
}
//REVISIT: do we really need to support block names as in Unicode 3.1
// or we can just create all the names in IsBLOCKNAME format (XML Schema REC)?
//
StringBuffer buffer = new StringBuffer(50);
for (int i = 0; i < Token.blockNames.length; i ++) {
Token r1 = Token.createRange();
int location;
if (i < NONBMP_BLOCK_START) {
location = i*2;
int rstart = Token.blockRanges.charAt(location);
int rend = Token.blockRanges.charAt(location+1);
//DEBUGING
//System.out.println(n+" " +Integer.toHexString(rstart)
// +"-"+ Integer.toHexString(rend));
r1.addRange(rstart, rend);
} else {
location = (i - NONBMP_BLOCK_START) * 2;
r1.addRange(Token.nonBMPBlockRanges[location],
Token.nonBMPBlockRanges[location + 1]);
}
String n = Token.blockNames[i];
if (n.equals("Specials"))
r1.addRange(0xfff0, 0xfffd);
if (n.equals("Private Use")) {
r1.addRange(0xF0000,0xFFFFD);
r1.addRange(0x100000,0x10FFFD);
}
Token.categories.put(n, r1);
Token.categories2.put(n, Token.complementRanges(r1));
buffer.setLength(0);
buffer.append("Is");
if (n.indexOf(' ') >= 0) {
for (int ci = 0; ci < n.length(); ci ++)
if (n.charAt(ci) != ' ') buffer.append((char)n.charAt(ci));
}
else {
buffer.append(n);
}
Token.setAlias(buffer.toString(), n, true);
}
// TR#18 1.2
Token.setAlias("ASSIGNED", "Cn", false);
Token.setAlias("UNASSIGNED", "Cn", true);
Token all = Token.createRange();
all.addRange(0, Token.UTF16_MAX);
Token.categories.put("ALL", all);
Token.categories2.put("ALL", Token.complementRanges(all));
Token.registerNonXS("ASSIGNED");
Token.registerNonXS("UNASSIGNED");
Token.registerNonXS("ALL");
Token isalpha = Token.createRange();
isalpha.mergeRanges(ranges[Character.UPPERCASE_LETTER]); // Lu
isalpha.mergeRanges(ranges[Character.LOWERCASE_LETTER]); // Ll
isalpha.mergeRanges(ranges[Character.OTHER_LETTER]); // Lo
Token.categories.put("IsAlpha", isalpha);
Token.categories2.put("IsAlpha", Token.complementRanges(isalpha));
Token.registerNonXS("IsAlpha");
Token isalnum = Token.createRange();
isalnum.mergeRanges(isalpha); // Lu Ll Lo
isalnum.mergeRanges(ranges[Character.DECIMAL_DIGIT_NUMBER]); // Nd
Token.categories.put("IsAlnum", isalnum);
Token.categories2.put("IsAlnum", Token.complementRanges(isalnum));
Token.registerNonXS("IsAlnum");
Token isspace = Token.createRange();
isspace.mergeRanges(Token.token_spaces);
isspace.mergeRanges(ranges[CHAR_SEPARATOR]); // Z
Token.categories.put("IsSpace", isspace);
Token.categories2.put("IsSpace", Token.complementRanges(isspace));
Token.registerNonXS("IsSpace");
Token isword = Token.createRange();
isword.mergeRanges(isalnum); // Lu Ll Lo Nd
isword.addRange('_', '_');
Token.categories.put("IsWord", isword);
Token.categories2.put("IsWord", Token.complementRanges(isword));
Token.registerNonXS("IsWord");
Token isascii = Token.createRange();
isascii.addRange(0, 127);
Token.categories.put("IsASCII", isascii);
Token.categories2.put("IsASCII", Token.complementRanges(isascii));
Token.registerNonXS("IsASCII");
Token isnotgraph = Token.createRange();
isnotgraph.mergeRanges(ranges[CHAR_OTHER]);
isnotgraph.addRange(' ', ' ');
Token.categories.put("IsGraph", Token.complementRanges(isnotgraph));
Token.categories2.put("IsGraph", isnotgraph);
Token.registerNonXS("IsGraph");
Token isxdigit = Token.createRange();
isxdigit.addRange('0', '9');
isxdigit.addRange('A', 'F');
isxdigit.addRange('a', 'f');
Token.categories.put("IsXDigit", Token.complementRanges(isxdigit));
Token.categories2.put("IsXDigit", isxdigit);
Token.registerNonXS("IsXDigit");
Token.setAlias("IsDigit", "Nd", true);
Token.setAlias("IsUpper", "Lu", true);
Token.setAlias("IsLower", "Ll", true);
Token.setAlias("IsCntrl", "C", true);
Token.setAlias("IsPrint", "C", false);
Token.setAlias("IsPunct", "P", true);
Token.registerNonXS("IsDigit");
Token.registerNonXS("IsUpper");
Token.registerNonXS("IsLower");
Token.registerNonXS("IsCntrl");
Token.registerNonXS("IsPrint");
Token.registerNonXS("IsPunct");
Token.setAlias("alpha", "IsAlpha", true);
Token.setAlias("alnum", "IsAlnum", true);
Token.setAlias("ascii", "IsASCII", true);
Token.setAlias("cntrl", "IsCntrl", true);
Token.setAlias("digit", "IsDigit", true);
Token.setAlias("graph", "IsGraph", true);
Token.setAlias("lower", "IsLower", true);
Token.setAlias("print", "IsPrint", true);
Token.setAlias("punct", "IsPunct", true);
Token.setAlias("space", "IsSpace", true);
Token.setAlias("upper", "IsUpper", true);
Token.setAlias("word", "IsWord", true); // Perl extension
Token.setAlias("xdigit", "IsXDigit", true);
Token.registerNonXS("alpha");
Token.registerNonXS("alnum");
Token.registerNonXS("ascii");
Token.registerNonXS("cntrl");
Token.registerNonXS("digit");
Token.registerNonXS("graph");
Token.registerNonXS("lower");
Token.registerNonXS("print");
Token.registerNonXS("punct");
Token.registerNonXS("space");
Token.registerNonXS("upper");
Token.registerNonXS("word");
Token.registerNonXS("xdigit");
} // synchronized
} // if null
RangeToken tok = positive ? (RangeToken)Token.categories.get(name)
: (RangeToken)Token.categories2.get(name);
//if (tok == null) System.out.println(name);
return tok;
}
static protected RangeToken getRange(String name, boolean positive, boolean xs) {
RangeToken range = Token.getRange(name, positive);
if (xs && range != null && Token.isRegisterNonXS(name))
range = null;
return range;
}
static Hashtable nonxs = null;
/**
* This method is called by only getRange().
* So this method need not MT-safe.
*/
static protected void registerNonXS(String name) {
if (Token.nonxs == null)
Token.nonxs = new Hashtable();
Token.nonxs.put(name, name);
}
static protected boolean isRegisterNonXS(String name) {
if (Token.nonxs == null)
return false;
//DEBUG
//System.err.println("isRegisterNonXS: "+name);
return Token.nonxs.containsKey(name);
}
private static void setAlias(String newName, String name, boolean positive) {
Token t1 = (Token)Token.categories.get(name);
Token t2 = (Token)Token.categories2.get(name);
if (positive) {
Token.categories.put(newName, t1);
Token.categories2.put(newName, t2);
} else {
Token.categories2.put(newName, t1);
Token.categories.put(newName, t2);
}
}
// ------------------------------------------------------
static final String viramaString =
"\u094D"// ;DEVANAGARI SIGN VIRAMA;Mn;9;ON;;;;;N;;;;;
+"\u09CD"//;BENGALI SIGN VIRAMA;Mn;9;ON;;;;;N;;;;;
+"\u0A4D"//;GURMUKHI SIGN VIRAMA;Mn;9;ON;;;;;N;;;;;
+"\u0ACD"//;GUJARATI SIGN VIRAMA;Mn;9;ON;;;;;N;;;;;
+"\u0B4D"//;ORIYA SIGN VIRAMA;Mn;9;ON;;;;;N;;;;;
+"\u0BCD"//;TAMIL SIGN VIRAMA;Mn;9;ON;;;;;N;;;;;
+"\u0C4D"//;TELUGU SIGN VIRAMA;Mn;9;ON;;;;;N;;;;;
+"\u0CCD"//;KANNADA SIGN VIRAMA;Mn;9;ON;;;;;N;;;;;
+"\u0D4D"//;MALAYALAM SIGN VIRAMA;Mn;9;ON;;;;;N;;;;;
+"\u0E3A"//;THAI CHARACTER PHINTHU;Mn;9;ON;;;;;N;THAI VOWEL SIGN PHINTHU;;;;
+"\u0F84";//;TIBETAN MARK HALANTA;Mn;9;ON;;;;;N;TIBETAN VIRAMA;;;;
static private Token token_grapheme = null;
static synchronized Token getGraphemePattern() {
if (Token.token_grapheme != null)
return Token.token_grapheme;
Token base_char = Token.createRange(); // [{ASSIGNED}]-[{M},{C}]
base_char.mergeRanges(Token.getRange("ASSIGNED", true));
base_char.subtractRanges(Token.getRange("M", true));
base_char.subtractRanges(Token.getRange("C", true));
Token virama = Token.createRange();
for (int i = 0; i < Token.viramaString.length(); i ++) {
/*int ch =*/ viramaString.charAt(i);
virama.addRange(i, i);
}
Token combiner_wo_virama = Token.createRange();
combiner_wo_virama.mergeRanges(Token.getRange("M", true));
combiner_wo_virama.addRange(0x1160, 0x11ff); // hangul_medial and hangul_final
combiner_wo_virama.addRange(0xff9e, 0xff9f); // extras
Token left = Token.createUnion(); // base_char?
left.addChild(base_char);
left.addChild(Token.token_empty);
Token foo = Token.createUnion();
foo.addChild(Token.createConcat(virama, Token.getRange("L", true)));
foo.addChild(combiner_wo_virama);
foo = Token.createClosure(foo);
foo = Token.createConcat(left, foo);
Token.token_grapheme = foo;
return Token.token_grapheme;
}
/**
* Combing Character Sequence in Perl 5.6.
*/
static private Token token_ccs = null;
static synchronized Token getCombiningCharacterSequence() {
if (Token.token_ccs != null)
return Token.token_ccs;
Token foo = Token.createClosure(Token.getRange("M", true)); // \pM*
foo = Token.createConcat(Token.getRange("M", false), foo); // \PM + \pM*
Token.token_ccs = foo;
return Token.token_ccs;
}
// ------------------------------------------------------
// ------------------------------------------------------
/**
* This class represents a node in parse tree.
*/
static class StringToken extends Token implements java.io.Serializable {
String string;
int refNumber;
StringToken(int type, String str, int n) {
super(type);
this.string = str;
this.refNumber = n;
}
int getReferenceNumber() { // for STRING
return this.refNumber;
}
String getString() { // for STRING
return this.string;
}
public String toString(int options) {
if (this.type == BACKREFERENCE)
return "\\"+this.refNumber;
else
return REUtil.quoteMeta(this.string);
}
}
/**
* This class represents a node in parse tree.
*/
static class ConcatToken extends Token implements java.io.Serializable {
Token child;
Token child2;
ConcatToken(Token t1, Token t2) {
super(Token.CONCAT);
this.child = t1;
this.child2 = t2;
}
int size() {
return 2;
}
Token getChild(int index) {
return index == 0 ? this.child : this.child2;
}
public String toString(int options) {
String ret;
if (this.child2.type == CLOSURE && this.child2.getChild(0) == this.child) {
ret = this.child.toString(options)+"+";
} else if (this.child2.type == NONGREEDYCLOSURE && this.child2.getChild(0) == this.child) {
ret = this.child.toString(options)+"+?";
} else
ret = this.child.toString(options)+this.child2.toString(options);
return ret;
}
}
/**
* This class represents a node in parse tree.
*/
static class CharToken extends Token implements java.io.Serializable {
int chardata;
CharToken(int type, int ch) {
super(type);
this.chardata = ch;
}
int getChar() {
return this.chardata;
}
public String toString(int options) {
String ret;
switch (this.type) {
case CHAR:
switch (this.chardata) {
case '|': case '*': case '+': case '?':
case '(': case ')': case '.': case '[':
case '{': case '\\':
ret = "\\"+(char)this.chardata;
break;
case '\f': ret = "\\f"; break;
case '\n': ret = "\\n"; break;
case '\r': ret = "\\r"; break;
case '\t': ret = "\\t"; break;
case 0x1b: ret = "\\e"; break;
//case 0x0b: ret = "\\v"; break;
default:
if (this.chardata >= 0x10000) {
String pre = "0"+Integer.toHexString(this.chardata);
ret = "\\v"+pre.substring(pre.length()-6, pre.length());
} else
ret = ""+(char)this.chardata;
}
break;
case ANCHOR:
if (this == Token.token_linebeginning || this == Token.token_lineend)
ret = ""+(char)this.chardata;
else
ret = "\\"+(char)this.chardata;
break;
default:
ret = null;
}
return ret;
}
boolean match(int ch) {
if (this.type == CHAR) {
return ch == this.chardata;
} else
throw new RuntimeException("NFAArrow#match(): Internal error: "+this.type);
}
}
/**
* This class represents a node in parse tree.
*/
static class ClosureToken extends Token implements java.io.Serializable {
int min;
int max;
Token child;
ClosureToken(int type, Token tok) {
super(type);
this.child = tok;
this.setMin(-1);
this.setMax(-1);
}
int size() {
return 1;
}
Token getChild(int index) {
return this.child;
}
final void setMin(int min) {
this.min = min;
}
final void setMax(int max) {
this.max = max;
}
final int getMin() {
return this.min;
}
final int getMax() {
return this.max;
}
public String toString(int options) {
String ret;
if (this.type == CLOSURE) {
if (this.getMin() < 0 && this.getMax() < 0) {
ret = this.child.toString(options)+"*";
} else if (this.getMin() == this.getMax()) {
ret = this.child.toString(options)+"{"+this.getMin()+"}";
} else if (this.getMin() >= 0 && this.getMax() >= 0) {
ret = this.child.toString(options)+"{"+this.getMin()+","+this.getMax()+"}";
} else if (this.getMin() >= 0 && this.getMax() < 0) {
ret = this.child.toString(options)+"{"+this.getMin()+",}";
} else
throw new RuntimeException("Token#toString(): CLOSURE "
+this.getMin()+", "+this.getMax());
} else {
if (this.getMin() < 0 && this.getMax() < 0) {
ret = this.child.toString(options)+"*?";
} else if (this.getMin() == this.getMax()) {
ret = this.child.toString(options)+"{"+this.getMin()+"}?";
} else if (this.getMin() >= 0 && this.getMax() >= 0) {
ret = this.child.toString(options)+"{"+this.getMin()+","+this.getMax()+"}?";
} else if (this.getMin() >= 0 && this.getMax() < 0) {
ret = this.child.toString(options)+"{"+this.getMin()+",}?";
} else
throw new RuntimeException("Token#toString(): NONGREEDYCLOSURE "
+this.getMin()+", "+this.getMax());
}
return ret;
}
}
/**
* This class represents a node in parse tree.
*/
static class ParenToken extends Token implements java.io.Serializable {
Token child;
int parennumber;
ParenToken(int type, Token tok, int paren) {
super(type);
this.child = tok;
this.parennumber = paren;
}
int size() {
return 1;
}
Token getChild(int index) {
return this.child;
}
int getParenNumber() {
return this.parennumber;
}
public String toString(int options) {
String ret = null;
switch (this.type) {
case PAREN:
if (this.parennumber == 0) {
ret = "(?:"+this.child.toString(options)+")";
} else {
ret = "("+this.child.toString(options)+")";
}
break;
case LOOKAHEAD:
ret = "(?="+this.child.toString(options)+")";
break;
case NEGATIVELOOKAHEAD:
ret = "(?!"+this.child.toString(options)+")";
break;
case LOOKBEHIND:
ret = "(?<="+this.child.toString(options)+")";
break;
case NEGATIVELOOKBEHIND:
ret = "(?"+this.child.toString(options)+")";
break;
}
return ret;
}
}
/**
* (?(condition)yes-pattern|no-pattern)
*/
static class ConditionToken extends Token implements java.io.Serializable {
int refNumber;
Token condition;
Token yes;
Token no;
ConditionToken(int refno, Token cond, Token yespat, Token nopat) {
super(Token.CONDITION);
this.refNumber = refno;
this.condition = cond;
this.yes = yespat;
this.no = nopat;
}
int size() {
return this.no == null ? 1 : 2;
}
Token getChild(int index) {
if (index == 0) return this.yes;
if (index == 1) return this.no;
throw new RuntimeException("Internal Error: "+index);
}
public String toString(int options) {
String ret;
if (refNumber > 0) {
ret = "(?("+refNumber+")";
} else if (this.condition.type == Token.ANCHOR) {
ret = "(?("+this.condition+")";
} else {
ret = "(?"+this.condition;
}
if (this.no == null) {
ret += this.yes+")";
} else {
ret += this.yes+"|"+this.no+")";
}
return ret;
}
}
/**
* (ims-ims: .... )
*/
static class ModifierToken extends Token implements java.io.Serializable {
Token child;
int add;
int mask;
ModifierToken(Token tok, int add, int mask) {
super(Token.MODIFIERGROUP);
this.child = tok;
this.add = add;
this.mask = mask;
}
int size() {
return 1;
}
Token getChild(int index) {
return this.child;
}
int getOptions() {
return this.add;
}
int getOptionsMask() {
return this.mask;
}
public String toString(int options) {
return "(?"
+(this.add == 0 ? "" : REUtil.createOptionString(this.add))
+(this.mask == 0 ? "" : REUtil.createOptionString(this.mask))
+":"
+this.child.toString(options)
+")";
}
}
/**
* This class represents a node in parse tree.
* for UNION or CONCAT.
*/
static class UnionToken extends Token implements java.io.Serializable {
Vector children;
UnionToken(int type) {
super(type);
}
void addChild(Token tok) {
if (tok == null) return;
if (this.children == null) this.children = new Vector();
if (this.type == UNION) {
this.children.addElement(tok);
return;
}
// This is CONCAT, and new child is CONCAT.
if (tok.type == CONCAT) {
for (int i = 0; i < tok.size(); i ++)
this.addChild(tok.getChild(i)); // Recursion
return;
}
int size = this.children.size();
if (size == 0) {
this.children.addElement(tok);
return;
}
Token previous = (Token)this.children.elementAt(size-1);
if (!((previous.type == CHAR || previous.type == STRING)
&& (tok.type == CHAR || tok.type == STRING))) {
this.children.addElement(tok);
return;
}
//System.err.println("Merge '"+previous+"' and '"+tok+"'.");
StringBuffer buffer;
int nextMaxLength = (tok.type == CHAR ? 2 : tok.getString().length());
if (previous.type == CHAR) { // Replace previous token by STRING
buffer = new StringBuffer(2 + nextMaxLength);
int ch = previous.getChar();
if (ch >= 0x10000)
buffer.append(REUtil.decomposeToSurrogates(ch));
else
buffer.append((char)ch);
previous = Token.createString(null);
this.children.setElementAt(previous, size-1);
} else { // STRING
buffer = new StringBuffer(previous.getString().length() + nextMaxLength);
buffer.append(previous.getString());
}
if (tok.type == CHAR) {
int ch = tok.getChar();
if (ch >= 0x10000)
buffer.append(REUtil.decomposeToSurrogates(ch));
else
buffer.append((char)ch);
} else {
buffer.append(tok.getString());
}
((StringToken)previous).string = new String(buffer);
}
int size() {
return this.children == null ? 0 : this.children.size();
}
Token getChild(int index) {
return (Token)this.children.elementAt(index);
}
public String toString(int options) {
String ret;
if (this.type == CONCAT) {
if (this.children.size() == 2) {
Token ch = this.getChild(0);
Token ch2 = this.getChild(1);
if (ch2.type == CLOSURE && ch2.getChild(0) == ch) {
ret = ch.toString(options)+"+";
} else if (ch2.type == NONGREEDYCLOSURE && ch2.getChild(0) == ch) {
ret = ch.toString(options)+"+?";
} else
ret = ch.toString(options)+ch2.toString(options);
} else {
StringBuffer sb = new StringBuffer();
for (int i = 0; i < this.children.size(); i ++) {
sb.append(((Token)this.children.elementAt(i)).toString(options));
}
ret = new String(sb);
}
return ret;
}
if (this.children.size() == 2 && this.getChild(1).type == EMPTY) {
ret = this.getChild(0).toString(options)+"?";
} else if (this.children.size() == 2
&& this.getChild(0).type == EMPTY) {
ret = this.getChild(1).toString(options)+"??";
} else {
StringBuffer sb = new StringBuffer();
sb.append(((Token)this.children.elementAt(0)).toString(options));
for (int i = 1; i < this.children.size(); i ++) {
sb.append((char)'|');
sb.append(((Token)this.children.elementAt(i)).toString(options));
}
ret = new String(sb);
}
return ret;
}
}
}
msv-2009.1/xsdlib/src-apache/com/sun/msv/datatype/regexp/RegularExpression.java 0000644 0001750 0001750 00000402007 10223107437 027736 0 ustar giovanni giovanni /*
* The Apache Software License, Version 1.1
*
*
* Copyright (c) 1999-2002 The Apache Software Foundation. All rights
* reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
*
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
*
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in
* the documentation and/or other materials provided with the
* distribution.
*
* 3. The end-user documentation included with the redistribution,
* if any, must include the following acknowledgment:
* "This product includes software developed by the
* Apache Software Foundation (http://www.apache.org/)."
* Alternately, this acknowledgment may appear in the software itself,
* if and wherever such third-party acknowledgments normally appear.
*
* 4. The names "Xerces" and "Apache Software Foundation" must
* not be used to endorse or promote products derived from this
* software without prior written permission. For written
* permission, please contact apache@apache.org.
*
* 5. Products derived from this software may not be called "Apache",
* nor may "Apache" appear in their name, without prior written
* permission of the Apache Software Foundation.
*
* THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESSED OR IMPLIED
* WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
* OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
* DISCLAIMED. IN NO EVENT SHALL THE APACHE SOFTWARE FOUNDATION OR
* ITS CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
* SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
* LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF
* USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
* ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
* OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT
* OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
* SUCH DAMAGE.
* ====================================================================
*
* This software consists of voluntary contributions made by many
* individuals on behalf of the Apache Software Foundation and was
* originally based on software copyright (c) 1999, International
* Business Machines, Inc., http://www.apache.org. For more
* information on the Apache Software Foundation, please see
* .
*/
package com.sun.msv.datatype.regexp;
import java.text.CharacterIterator;
/**
* A regular expression matching engine using Non-deterministic Finite Automaton (NFA).
* This engine does not conform to the POSIX regular expression.
*
*
*
How to use
*
*
*
A. Standard way
*
*
* RegularExpression re = new RegularExpression(regex);
* if (re.matches(text)) { ... }
*
*
*
B. Capturing groups
*
*
* RegularExpression re = new RegularExpression(regex);
* Match match = new Match();
* if (re.matches(text, match)) {
* ... // You can refer captured texts with methods of the Match class.
* }
*
*
*
*
*
Case-insensitive matching
*
* RegularExpression re = new RegularExpression(regex, "i");
* if (re.matches(text) >= 0) { ...}
*
By this option, \b \B \< \> are processed with the method of
* 'Unicode Regular Expression Guidelines' Revision 4.
* When "w" and "u" are specified at the same time,
* \b \B \< \> are processed for the "w" option.
*
The parser treats a comma in a character class as a range separator.
* [a,b] matches a or , or b without this option.
* [a,b] matches a or b with this option.
*
*
* By this option, the engine confoms to XML Schema: Regular Expression.
* The match() method does not do subsring matching
* but entire string matching.
*
*
*
*
*
Syntax
*
*
*
*
Differences from the Perl 5 regular expression
*
*
There is 6-digit hexadecimal character representation (\u005cvHHHHHH.)
*
Supports subtraction, union, and intersection operations for character classes.
*
Matches any one character except the following characters.
*
LINE FEED (U+000A), CARRIAGE RETURN (U+000D),
* PARAGRAPH SEPARATOR (U+2029), LINE SEPARATOR (U+2028)
*
This expression matches one code point in Unicode. It can match a pair of surrogates.
*
When the "s" option is specified,
* it matches any character including the above four characters.
*
*
\e \f \n \r \t
*
Matches ESCAPE (U+001B), FORM FEED (U+000C), LINE FEED (U+000A),
* CARRIAGE RETURN (U+000D), HORIZONTAL TABULATION (U+0009)
*
*
\cC
*
Matches a control character.
* The C must be one of '@', 'A'-'Z',
* '[', '\u005c', ']', '^', '_'.
* It matches a control character of which the character code is less than
* the character code of the C by 0x0040.
*
For example, a \cJ matches a LINE FEED (U+000A),
* and a \c[ matches an ESCAPE (U+001B).
*
*
a non-meta character
*
Matches the character.
*
*
\ + a meta character
*
Matches the meta character.
*
*
\u005cxHH\u005cx{HHHH}
*
Matches a character of which code point is HH (Hexadecimal) in Unicode.
* You can write just 2 digits for \u005cxHH, and
* variable length digits for \u005cx{HHHH}.
*
*
*
*
\u005cvHHHHHH
*
Matches a character of which code point is HHHHHH (Hexadecimal) in Unicode.
*
*
\g
*
Matches a grapheme.
*
It is equivalent to (?[\p{ASSIGNED}]-[\p{M}\p{C}])?(?:\p{M}|[\x{094D}\x{09CD}\x{0A4D}\x{0ACD}\x{0B3D}\x{0BCD}\x{0C4D}\x{0CCD}\x{0D4D}\x{0E3A}\x{0F84}]\p{L}|[\x{1160}-\x{11A7}]|[\x{11A8}-\x{11FF}]|[\x{FF9E}\x{FF9F}])*
*
*
\X
*
Matches a combining character sequence.
* It is equivalent to (?:\PM\pM*)
*
Positive character class. It matches a character in ranges.
*
Rn:
*
*
A character (including \e \f \n \r \t\u005cxHH\u005cx{HHHH}\u005cvHHHHHH)
*
This range matches the character.
*
C1-C2
*
This range matches a character which has a code point that is >= C1's code point and <= C2's code point.
+ *
A POSIX character class: [:alpha:] [:alnum:] [:ascii:] [:cntrl:] [:digit:] [:graph:] [:lower:] [:print:] [:punct:] [:space:] [:upper:] [:xdigit:],
+ * and negative POSIX character classes in Perl like [:^alpha:]
*
...
*
\d \D \s \S \w \W \p{name} \P{name}
*
These expressions specifies the same ranges as the following expressions.
*
*
Enumerated ranges are merged (union operation).
* [a-ec-z] is equivalent to [a-z]
*
*
Negative character class. It matches a character not in ranges.
*
*
(?[ranges]op[ranges]op[ranges] ... )
* (op is - or + or &.)
*
Subtraction or union or intersection for character classes.
*
For exmaple, (?[A-Z]-[CF]) is equivalent to [A-BD-EG-Z], and (?[0x00-0x7f]-[K]&[\p{Lu}]) is equivalent to [A-JL-Z].
*
The result of this operations is a positive character class
* even if an expression includes any negative character classes.
* You have to take care on this in case-insensitive matching.
* For instance, (?[^b]) is equivalent to [\x00-ac-\x{10ffff}],
* which is equivalent to [^b] in case-sensitive matching.
* But, in case-insensitive matching, (?[^b]) matches any character because
* it includes 'B' and 'B' matches 'b'
* though [^b] is processed as [^Bb].
*
*
Character class subtraction for the XML Schema.
* You can use this syntax when you specify an "X" option.
*
*
\d
*
Equivalent to [0-9].
*
When a "u" option is set, it is equivalent to
* \p{Nd}.
*
*
\D
*
Equivalent to [^0-9]
*
When a "u" option is set, it is equivalent to
* \P{Nd}.
*
*
\s
*
Equivalent to [ \f\n\r\t]
*
When a "u" option is set, it is equivalent to
* [ \f\n\r\t\p{Z}].
*
*
\S
*
Equivalent to [^ \f\n\r\t]
*
When a "u" option is set, it is equivalent to
* [^ \f\n\r\t\p{Z}].
*
*
\w
*
Equivalent to [a-zA-Z0-9_]
*
When a "u" option is set, it is equivalent to
* [\p{Lu}\p{Ll}\p{Lo}\p{Nd}_].
*
*
\W
*
Equivalent to [^a-zA-Z0-9_]
*
When a "u" option is set, it is equivalent to
* [^\p{Lu}\p{Ll}\p{Lo}\p{Nd}_].
*
*
\p{name}
*
Matches one character in the specified General Category (the second field in UnicodeData.txt) or the specified Block.
* The following names are available:
*
*
Unicode General Categories:
*
* L, M, N, Z, C, P, S, Lu, Ll, Lt, Lm, Lo, Mn, Me, Mc, Nd, Nl, No, Zs, Zl, Zp,
* Cc, Cf, Cn, Co, Cs, Pd, Ps, Pe, Pc, Po, Sm, Sc, Sk, So,
*
*
(Currently the Cn category includes U+10000-U+10FFFF characters)
*
Unicode Blocks:
*
* Basic Latin, Latin-1 Supplement, Latin Extended-A, Latin Extended-B,
* IPA Extensions, Spacing Modifier Letters, Combining Diacritical Marks, Greek,
* Cyrillic, Armenian, Hebrew, Arabic, Devanagari, Bengali, Gurmukhi, Gujarati,
* Oriya, Tamil, Telugu, Kannada, Malayalam, Thai, Lao, Tibetan, Georgian,
* Hangul Jamo, Latin Extended Additional, Greek Extended, General Punctuation,
* Superscripts and Subscripts, Currency Symbols, Combining Marks for Symbols,
* Letterlike Symbols, Number Forms, Arrows, Mathematical Operators,
* Miscellaneous Technical, Control Pictures, Optical Character Recognition,
* Enclosed Alphanumerics, Box Drawing, Block Elements, Geometric Shapes,
* Miscellaneous Symbols, Dingbats, CJK Symbols and Punctuation, Hiragana,
* Katakana, Bopomofo, Hangul Compatibility Jamo, Kanbun,
* Enclosed CJK Letters and Months, CJK Compatibility, CJK Unified Ideographs,
* Hangul Syllables, High Surrogates, High Private Use Surrogates, Low Surrogates,
* Private Use, CJK Compatibility Ideographs, Alphabetic Presentation Forms,
* Arabic Presentation Forms-A, Combining Half Marks, CJK Compatibility Forms,
* Small Form Variants, Arabic Presentation Forms-B, Specials,
* Halfwidth and Fullwidth Forms
*
*
Others:
*
ALL (Equivalent to [\u005cu0000-\u005cv10FFFF])
*
ASSGINED (\p{ASSIGNED} is equivalent to \P{Cn})
*
UNASSGINED
* (\p{UNASSIGNED} is equivalent to \p{Cn})
*
*
*
\P{name}
*
Matches one character not in the specified General Category or the specified Block.
*
*
*
*
Selection and Quantifier
*
*
X|Y
*
...
*
*
X*
*
Matches 0 or more X.
*
*
X+
*
Matches 1 or more X.
*
*
X?
*
Matches 0 or 1 X.
*
*
X{number}
*
Matches number times.
*
*
X{min,}
*
...
*
*
X{min,max}
*
...
*
*
X*?
*
X+?
*
X??
*
X{min,}?
*
X{min,max}?
*
Non-greedy matching.
*
*
*
*
Grouping, Capturing, and Back-reference
*
*
(?:X)
*
Grouping. "foo+" matches "foo" or "foooo".
* If you want it matches "foofoo" or "foofoofoo",
* you have to write "(?:foo)+".
*
*
(X)
*
Grouping with capturing.
* It make a group and applications can know
* where in target text a group matched with methods of a Match instance
* after matches(String,Match).
* The 0th group means whole of this regular expression.
* The Nth gorup is the inside of the Nth left parenthesis.
*
*
For instance, a regular expression is
* " *([^<:]*) +<([^>]*)> *"
* and target text is
* "From: TAMURA Kent <kent@trl.ibm.co.jp>":
*
*
Match.getCapturedText(0):
* " TAMURA Kent <kent@trl.ibm.co.jp>"
*
The options or the options2 consists of 'i' 'm' 's' 'w'.
* Note that it can not contain 'u'.
*
*
(?options)
*
(?options-options2)
*
......
*
These expressions must be at the beginning of a group.
*
*
*
*
Anchor
*
*
\A
*
Matches the beginnig of the text.
*
*
\Z
*
Matches the end of the text, or before an EOL character at the end of the text,
* or CARRIAGE RETURN + LINE FEED at the end of the text.
*
*
\z
*
Matches the end of the text.
*
*
^
*
Matches the beginning of the text. It is equivalent to \A.
*
When a "m" option is set,
* it matches the beginning of the text, or after one of EOL characters (
* LINE FEED (U+000A), CARRIAGE RETURN (U+000D), LINE SEPARATOR (U+2028),
* PARAGRAPH SEPARATOR (U+2029).)
*
*
$
*
Matches the end of the text, or before an EOL character at the end of the text,
* or CARRIAGE RETURN + LINE FEED at the end of the text.
*
When a "m" option is set,
* it matches the end of the text, or before an EOL character.
*
*
*/
public static void main(String[] argv) {
String pattern = null;
try {
String options = "";
String target = null;
if( argv.length == 0 ) {
System.out.println( "Error:Usage: java REUtil -i|-m|-s|-u|-w|-X regularExpression String" );
System.exit( 0 );
}
for (int i = 0; i < argv.length; i ++) {
if (argv[i].length() == 0 || argv[i].charAt(0) != '-') {
if (pattern == null)
pattern = argv[i];
else if (target == null)
target = argv[i];
else
System.err.println("Unnecessary: "+argv[i]);
} else if (argv[i].equals("-i")) {
options += "i";
} else if (argv[i].equals("-m")) {
options += "m";
} else if (argv[i].equals("-s")) {
options += "s";
} else if (argv[i].equals("-u")) {
options += "u";
} else if (argv[i].equals("-w")) {
options += "w";
} else if (argv[i].equals("-X")) {
options += "X";
} else {
System.err.println("Unknown option: "+argv[i]);
}
}
RegularExpression reg = new RegularExpression(pattern, options);
System.out.println("RegularExpression: "+reg);
Match match = new Match();
reg.matches(target, match);
for (int i = 0; i < match.getNumberOfGroups(); i ++) {
if (i == 0 ) System.out.print("Matched range for the whole pattern: ");
else System.out.print("["+i+"]: ");
if (match.getBeginning(i) < 0)
System.out.println("-1");
else {
System.out.print(match.getBeginning(i)+", "+match.getEnd(i)+", ");
System.out.println("\""+match.getCapturedText(i)+"\"");
}
}
} catch (ParseException pe) {
if (pattern == null) {
pe.printStackTrace();
} else {
System.err.println("org.apache.xerces.utils.regex.ParseException: "+pe.getMessage());
String indent = " ";
System.err.println(indent+pattern);
int loc = pe.getLocation();
if (loc >= 0) {
System.err.print(indent);
for (int i = 0; i < loc; i ++) System.err.print("-");
System.err.println("^");
}
}
} catch (Exception e) {
e.printStackTrace();
}
}
static final int CACHESIZE = 20;
static final RegularExpression[] regexCache = new RegularExpression[CACHESIZE];
/**
* Creates a RegularExpression instance.
* This method caches created instances.
*
* @see RegularExpression#RegularExpression(java.lang.String, java.lang.String)
*/
public static RegularExpression createRegex(String pattern, String options)
throws ParseException {
RegularExpression re = null;
int intOptions = REUtil.parseOptions(options);
synchronized (REUtil.regexCache) {
int i;
for (i = 0; i < REUtil.CACHESIZE; i ++) {
RegularExpression cached = REUtil.regexCache[i];
if (cached == null) {
i = -1;
break;
}
if (cached.equals(pattern, intOptions)) {
re = cached;
break;
}
}
if (re != null) {
if (i != 0) {
System.arraycopy(REUtil.regexCache, 0, REUtil.regexCache, 1, i);
REUtil.regexCache[0] = re;
}
} else {
re = new RegularExpression(pattern, options);
System.arraycopy(REUtil.regexCache, 0, REUtil.regexCache, 1, REUtil.CACHESIZE-1);
REUtil.regexCache[0] = re;
}
}
return re;
}
/**
*
* @see RegularExpression#matches(java.lang.String)
*/
public static boolean matches(String regex, String target) throws ParseException {
return REUtil.createRegex(regex, null).matches(target);
}
/**
*
* @see RegularExpression#matches(java.lang.String)
*/
public static boolean matches(String regex, String options, String target) throws ParseException {
return REUtil.createRegex(regex, options).matches(target);
}
// ================================================================
/**
*
*/
public static String quoteMeta(String literal) {
int len = literal.length();
StringBuffer buffer = null;
for (int i = 0; i < len; i ++) {
int ch = literal.charAt(i);
if (".*+?{[()|\\^$".indexOf(ch) >= 0) {
if (buffer == null) {
buffer = new StringBuffer(i+(len-i)*2);
if (i > 0) buffer.append(literal.substring(0, i));
}
buffer.append((char)'\\');
buffer.append((char)ch);
} else if (buffer != null)
buffer.append((char)ch);
}
return buffer != null ? buffer.toString() : literal;
}
// ================================================================
static void dumpString(String v) {
for (int i = 0; i < v.length(); i ++) {
System.out.print(Integer.toHexString(v.charAt(i)));
System.out.print(" ");
}
System.out.println();
}
}
msv-2009.1/xsdlib/src-apache/com/sun/msv/datatype/regexp/Match.java 0000644 0001750 0001750 00000017050 10223107437 025311 0 ustar giovanni giovanni /*
* The Apache Software License, Version 1.1
*
*
* Copyright (c) 1999-2002 The Apache Software Foundation. All rights
* reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
*
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
*
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in
* the documentation and/or other materials provided with the
* distribution.
*
* 3. The end-user documentation included with the redistribution,
* if any, must include the following acknowledgment:
* "This product includes software developed by the
* Apache Software Foundation (http://www.apache.org/)."
* Alternately, this acknowledgment may appear in the software itself,
* if and wherever such third-party acknowledgments normally appear.
*
* 4. The names "Xerces" and "Apache Software Foundation" must
* not be used to endorse or promote products derived from this
* software without prior written permission. For written
* permission, please contact apache@apache.org.
*
* 5. Products derived from this software may not be called "Apache",
* nor may "Apache" appear in their name, without prior written
* permission of the Apache Software Foundation.
*
* THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESSED OR IMPLIED
* WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
* OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
* DISCLAIMED. IN NO EVENT SHALL THE APACHE SOFTWARE FOUNDATION OR
* ITS CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
* SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
* LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF
* USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
* ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
* OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT
* OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
* SUCH DAMAGE.
* ====================================================================
*
* This software consists of voluntary contributions made by many
* individuals on behalf of the Apache Software Foundation and was
* originally based on software copyright (c) 1999, International
* Business Machines, Inc., http://www.apache.org. For more
* information on the Apache Software Foundation, please see
* .
*/
package com.sun.msv.datatype.regexp;
import java.text.CharacterIterator;
/**
*
* An instance of this class has ranges captured in matching.
*
* @see RegularExpression#matches(char[], int, int, Match)
* @see RegularExpression#matches(char[], Match)
* @see RegularExpression#matches(java.text.CharacterIterator, Match)
* @see RegularExpression#matches(java.lang.String, int, int, Match)
* @see RegularExpression#matches(java.lang.String, Match)
* @author TAMURA Kent <kent@trl.ibm.co.jp>
* @version Match.java,v 1.4 2002/08/09 15:18:17 neilg Exp
*/
final class Match implements Cloneable {
int[] beginpos = null;
int[] endpos = null;
int nofgroups = 0;
CharacterIterator ciSource = null;
String strSource = null;
char[] charSource = null;
/**
* Creates an instance.
*/
public Match() {
}
/**
*
*/
public synchronized Object clone() {
Match ma = new Match();
if (this.nofgroups > 0) {
ma.setNumberOfGroups(this.nofgroups);
if (this.ciSource != null) ma.setSource(this.ciSource);
if (this.strSource != null) ma.setSource(this.strSource);
for (int i = 0; i < this.nofgroups; i ++) {
ma.setBeginning(i, this.getBeginning(i));
ma.setEnd(i, this.getEnd(i));
}
}
return ma;
}
/**
*
*/
protected void setNumberOfGroups(int n) {
int oldn = this.nofgroups;
this.nofgroups = n;
if (oldn <= 0
|| oldn < n || n*2 < oldn) {
this.beginpos = new int[n];
this.endpos = new int[n];
}
for (int i = 0; i < n; i ++) {
this.beginpos[i] = -1;
this.endpos[i] = -1;
}
}
/**
*
*/
protected void setSource(CharacterIterator ci) {
this.ciSource = ci;
this.strSource = null;
this.charSource = null;
}
/**
*
*/
protected void setSource(String str) {
this.ciSource = null;
this.strSource = str;
this.charSource = null;
}
/**
*
*/
protected void setSource(char[] chars) {
this.ciSource = null;
this.strSource = null;
this.charSource = chars;
}
/**
*
*/
protected void setBeginning(int index, int v) {
this.beginpos[index] = v;
}
/**
*
*/
protected void setEnd(int index, int v) {
this.endpos[index] = v;
}
/**
* Return the number of regular expression groups.
* This method returns 1 when the regular expression has no capturing-parenthesis.
*/
public int getNumberOfGroups() {
if (this.nofgroups <= 0)
throw new IllegalStateException("A result is not set.");
return this.nofgroups;
}
/**
* Return a start position in the target text matched to specified regular expression group.
*
* @param index Less than getNumberOfGroups().
*/
public int getBeginning(int index) {
if (this.beginpos == null)
throw new IllegalStateException("A result is not set.");
if (index < 0 || this.nofgroups <= index)
throw new IllegalArgumentException("The parameter must be less than "
+this.nofgroups+": "+index);
return this.beginpos[index];
}
/**
* Return an end position in the target text matched to specified regular expression group.
*
* @param index Less than getNumberOfGroups().
*/
public int getEnd(int index) {
if (this.endpos == null)
throw new IllegalStateException("A result is not set.");
if (index < 0 || this.nofgroups <= index)
throw new IllegalArgumentException("The parameter must be less than "
+this.nofgroups+": "+index);
return this.endpos[index];
}
/**
* Return an substring of the target text matched to specified regular expression group.
*
* @param index Less than getNumberOfGroups().
*/
public String getCapturedText(int index) {
if (this.beginpos == null)
throw new IllegalStateException("match() has never been called.");
if (index < 0 || this.nofgroups <= index)
throw new IllegalArgumentException("The parameter must be less than "
+this.nofgroups+": "+index);
String ret;
int begin = this.beginpos[index], end = this.endpos[index];
if (begin < 0 || end < 0) return null;
if (this.ciSource != null) {
ret = REUtil.substring(this.ciSource, begin, end);
} else if (this.strSource != null) {
ret = this.strSource.substring(begin, end);
} else {
ret = new String(this.charSource, begin, end-begin);
}
return ret;
}
}
msv-2009.1/xsdlib/src-apache/com/sun/msv/datatype/regexp/ParserForXMLSchema.java 0000644 0001750 0001750 00000056611 10223107437 027670 0 ustar giovanni giovanni /*
* The Apache Software License, Version 1.1
*
*
* Copyright (c) 1999-2003 The Apache Software Foundation. All rights
* reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
*
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
*
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in
* the documentation and/or other materials provided with the
* distribution.
*
* 3. The end-user documentation included with the redistribution,
* if any, must include the following acknowledgment:
* "This product includes software developed by the
* Apache Software Foundation (http://www.apache.org/)."
* Alternately, this acknowledgment may appear in the software itself,
* if and wherever such third-party acknowledgments normally appear.
*
* 4. The names "Xerces" and "Apache Software Foundation" must
* not be used to endorse or promote products derived from this
* software without prior written permission. For written
* permission, please contact apache@apache.org.
*
* 5. Products derived from this software may not be called "Apache",
* nor may "Apache" appear in their name, without prior written
* permission of the Apache Software Foundation.
*
* THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESSED OR IMPLIED
* WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
* OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
* DISCLAIMED. IN NO EVENT SHALL THE APACHE SOFTWARE FOUNDATION OR
* ITS CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
* SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
* LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF
* USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
* ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
* OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT
* OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
* SUCH DAMAGE.
* ====================================================================
*
* This software consists of voluntary contributions made by many
* individuals on behalf of the Apache Software Foundation and was
* originally based on software copyright (c) 1999, International
* Business Machines, Inc., http://www.apache.org. For more
* information on the Apache Software Foundation, please see
* .
*/
package com.sun.msv.datatype.regexp;
import java.util.Hashtable;
import java.util.Locale;
/**
* A regular expression parser for the XML Shema.
*
* @author TAMURA Kent <kent@trl.ibm.co.jp>
* @version ParserForXMLSchema.java,v 1.5 2003/03/24 23:37:55 sandygao Exp
*/
class ParserForXMLSchema extends RegexParser {
public ParserForXMLSchema() {
//this.setLocale(Locale.getDefault());
}
public ParserForXMLSchema(Locale locale) {
//this.setLocale(locale);
}
Token processCaret() throws ParseException {
this.next();
return Token.createChar('^');
}
Token processDollar() throws ParseException {
this.next();
return Token.createChar('$');
}
Token processLookahead() throws ParseException {
throw ex("parser.process.1", this.offset);
}
Token processNegativelookahead() throws ParseException {
throw ex("parser.process.1", this.offset);
}
Token processLookbehind() throws ParseException {
throw ex("parser.process.1", this.offset);
}
Token processNegativelookbehind() throws ParseException {
throw ex("parser.process.1", this.offset);
}
Token processBacksolidus_A() throws ParseException {
throw ex("parser.process.1", this.offset);
}
Token processBacksolidus_Z() throws ParseException {
throw ex("parser.process.1", this.offset);
}
Token processBacksolidus_z() throws ParseException {
throw ex("parser.process.1", this.offset);
}
Token processBacksolidus_b() throws ParseException {
throw ex("parser.process.1", this.offset);
}
Token processBacksolidus_B() throws ParseException {
throw ex("parser.process.1", this.offset);
}
Token processBacksolidus_lt() throws ParseException {
throw ex("parser.process.1", this.offset);
}
Token processBacksolidus_gt() throws ParseException {
throw ex("parser.process.1", this.offset);
}
Token processStar(Token tok) throws ParseException {
this.next();
return Token.createClosure(tok);
}
Token processPlus(Token tok) throws ParseException {
// X+ -> XX*
this.next();
return Token.createConcat(tok, Token.createClosure(tok));
}
Token processQuestion(Token tok) throws ParseException {
// X? -> X|
this.next();
Token par = Token.createUnion();
par.addChild(tok);
par.addChild(Token.createEmpty());
return par;
}
boolean checkQuestion(int off) {
return false;
}
Token processParen() throws ParseException {
this.next();
Token tok = Token.createParen(this.parseRegex(), 0);
if (this.read() != super.T_RPAREN) throw ex("parser.factor.1", this.offset-1);
this.next(); // Skips ')'
return tok;
}
Token processParen2() throws ParseException {
throw ex("parser.process.1", this.offset);
}
Token processCondition() throws ParseException {
throw ex("parser.process.1", this.offset);
}
Token processModifiers() throws ParseException {
throw ex("parser.process.1", this.offset);
}
Token processIndependent() throws ParseException {
throw ex("parser.process.1", this.offset);
}
Token processBacksolidus_c() throws ParseException {
this.next();
return this.getTokenForShorthand('c');
}
Token processBacksolidus_C() throws ParseException {
this.next();
return this.getTokenForShorthand('C');
}
Token processBacksolidus_i() throws ParseException {
this.next();
return this.getTokenForShorthand('i');
}
Token processBacksolidus_I() throws ParseException {
this.next();
return this.getTokenForShorthand('I');
}
Token processBacksolidus_g() throws ParseException {
throw this.ex("parser.process.1", this.offset-2);
}
Token processBacksolidus_X() throws ParseException {
throw ex("parser.process.1", this.offset-2);
}
Token processBackreference() throws ParseException {
throw ex("parser.process.1", this.offset-4);
}
int processCIinCharacterClass(RangeToken tok, int c) {
tok.mergeRanges(this.getTokenForShorthand(c));
return -1;
}
/**
* Parses a character-class-expression, not a character-class-escape.
*
* c-c-expression ::= '[' c-group ']'
* c-group ::= positive-c-group | negative-c-group | c-c-subtraction
* positive-c-group ::= (c-range | c-c-escape)+
* negative-c-group ::= '^' positive-c-group
* c-c-subtraction ::= (positive-c-group | negative-c-group) subtraction
* subtraction ::= '-' c-c-expression
* c-range ::= single-range | from-to-range
* single-range ::= multi-c-escape | category-c-escape | block-c-escape |
* cc-normal-c ::=
* from-to-range ::= cc-normal-c '-' cc-normal-c
*
* @param useNrange Ignored.
* @return This returns no NrageToken.
*/
protected RangeToken parseCharacterClass(boolean useNrange) throws ParseException {
this.setContext(S_INBRACKETS);
this.next(); // '['
boolean nrange = false;
RangeToken base = null;
RangeToken tok;
if (this.read() == T_CHAR && this.chardata == '^') {
nrange = true;
this.next(); // '^'
base = Token.createRange();
base.addRange(0, Token.UTF16_MAX);
tok = Token.createRange();
} else {
tok = Token.createRange();
}
int type;
boolean firstloop = true;
while ((type = this.read()) != T_EOF) { // Don't use 'cotinue' for this loop.
// single-range | from-to-range | subtraction
if (type == T_CHAR && this.chardata == ']' && !firstloop) {
if (nrange) {
base.subtractRanges(tok);
tok = base;
}
break;
}
int c = this.chardata;
boolean end = false;
if (type == T_BACKSOLIDUS) {
switch (c) {
case 'd': case 'D':
case 'w': case 'W':
case 's': case 'S':
tok.mergeRanges(this.getTokenForShorthand(c));
end = true;
break;
case 'i': case 'I':
case 'c': case 'C':
c = this.processCIinCharacterClass(tok, c);
if (c < 0) end = true;
break;
case 'p':
case 'P':
int pstart = this.offset;
RangeToken tok2 = this.processBacksolidus_pP(c);
if (tok2 == null) throw this.ex("parser.atom.5", pstart);
tok.mergeRanges(tok2);
end = true;
break;
default:
c = this.decodeEscaped();
} // \ + c
} // backsolidus
else if (type == T_XMLSCHEMA_CC_SUBTRACTION && !firstloop) {
// Subraction
if (nrange) {
base.subtractRanges(tok);
tok = base;
}
RangeToken range2 = this.parseCharacterClass(false);
tok.subtractRanges(range2);
if (this.read() != T_CHAR || this.chardata != ']')
throw this.ex("parser.cc.5", this.offset);
break; // Exit this loop
}
this.next();
if (!end) { // if not shorthands...
if (type == T_CHAR) {
if (c == '[') throw this.ex("parser.cc.6", this.offset-2);
if (c == ']') throw this.ex("parser.cc.7", this.offset-2);
if (c == '-') throw this.ex("parser.cc.8", this.offset-2);
}
if (this.read() != T_CHAR || this.chardata != '-') { // Here is no '-'.
tok.addRange(c, c);
} else { // Found '-'
// Is this '-' is a from-to token??
this.next(); // Skips '-'
if ((type = this.read()) == T_EOF) throw this.ex("parser.cc.2", this.offset);
// c '-' ']' -> '-' is a single-range.
if ((type == T_CHAR && this.chardata == ']')
|| type == T_XMLSCHEMA_CC_SUBTRACTION) {
throw this.ex("parser.cc.8", this.offset-1);
} else {
int rangeend = this.chardata;
if (type == T_CHAR) {
if (rangeend == '[') throw this.ex("parser.cc.6", this.offset-1);
if (rangeend == ']') throw this.ex("parser.cc.7", this.offset-1);
if (rangeend == '-') throw this.ex("parser.cc.8", this.offset-2);
}
else if (type == T_BACKSOLIDUS)
rangeend = this.decodeEscaped();
this.next();
if (c > rangeend) throw this.ex("parser.ope.3", this.offset-1);
tok.addRange(c, rangeend);
}
}
}
firstloop = false;
}
if (this.read() == T_EOF)
throw this.ex("parser.cc.2", this.offset);
tok.sortRanges();
tok.compactRanges();
//tok.dumpRanges();
this.setContext(S_NORMAL);
this.next(); // Skips ']'
return tok;
}
protected RangeToken parseSetOperations() throws ParseException {
throw this.ex("parser.process.1", this.offset);
}
Token getTokenForShorthand(int ch) {
switch (ch) {
case 'd':
return ParserForXMLSchema.getRange("xml:isDigit", true);
case 'D':
return ParserForXMLSchema.getRange("xml:isDigit", false);
case 'w':
return ParserForXMLSchema.getRange("xml:isWord", true);
case 'W':
return ParserForXMLSchema.getRange("xml:isWord", false);
case 's':
return ParserForXMLSchema.getRange("xml:isSpace", true);
case 'S':
return ParserForXMLSchema.getRange("xml:isSpace", false);
case 'c':
return ParserForXMLSchema.getRange("xml:isNameChar", true);
case 'C':
return ParserForXMLSchema.getRange("xml:isNameChar", false);
case 'i':
return ParserForXMLSchema.getRange("xml:isInitialNameChar", true);
case 'I':
return ParserForXMLSchema.getRange("xml:isInitialNameChar", false);
default:
throw new RuntimeException("Internal Error: shorthands: \\u"+Integer.toString(ch, 16));
}
}
int decodeEscaped() throws ParseException {
if (this.read() != T_BACKSOLIDUS) throw ex("parser.next.1", this.offset-1);
int c = this.chardata;
switch (c) {
case 'n': c = '\n'; break; // LINE FEED U+000A
case 'r': c = '\r'; break; // CRRIAGE RETURN U+000D
case 't': c = '\t'; break; // HORIZONTAL TABULATION U+0009
case '\\':
case '|':
case '.':
case '^':
case '-':
case '?':
case '*':
case '+':
case '{':
case '}':
case '(':
case ')':
case '[':
case ']':
break; // return actucal char
default:
throw ex("parser.process.1", this.offset-2);
}
return c;
}
static private Hashtable ranges = null;
static private Hashtable ranges2 = null;
static synchronized protected RangeToken getRange(String name, boolean positive) {
if (ranges == null) {
ranges = new Hashtable();
ranges2 = new Hashtable();
Token tok = Token.createRange();
setupRange(tok, SPACES);
ranges.put("xml:isSpace", tok);
ranges2.put("xml:isSpace", Token.complementRanges(tok));
tok = Token.createRange();
setupRange(tok, DIGITS);
ranges.put("xml:isDigit", tok);
ranges2.put("xml:isDigit", Token.complementRanges(tok));
tok = Token.createRange();
setupRange(tok, DIGITS);
ranges.put("xml:isDigit", tok);
ranges2.put("xml:isDigit", Token.complementRanges(tok));
tok = Token.createRange();
setupRange(tok, LETTERS);
tok.mergeRanges((Token)ranges.get("xml:isDigit"));
ranges.put("xml:isWord", tok);
ranges2.put("xml:isWord", Token.complementRanges(tok));
tok = Token.createRange();
setupRange(tok, NAMECHARS);
ranges.put("xml:isNameChar", tok);
ranges2.put("xml:isNameChar", Token.complementRanges(tok));
tok = Token.createRange();
setupRange(tok, LETTERS);
tok.addRange('_', '_');
tok.addRange(':', ':');
ranges.put("xml:isInitialNameChar", tok);
ranges2.put("xml:isInitialNameChar", Token.complementRanges(tok));
}
RangeToken tok = positive ? (RangeToken)ranges.get(name)
: (RangeToken)ranges2.get(name);
return tok;
}
static void setupRange(Token range, String src) {
int len = src.length();
for (int i = 0; i < len; i += 2)
range.addRange(src.charAt(i), src.charAt(i+1));
}
private static final String SPACES = "\t\n\r\r ";
private static final String NAMECHARS =
"\u002d\u002e\u0030\u003a\u0041\u005a\u005f\u005f\u0061\u007a\u00b7\u00b7\u00c0\u00d6"
+"\u00d8\u00f6\u00f8\u0131\u0134\u013e\u0141\u0148\u014a\u017e\u0180\u01c3\u01cd\u01f0"
+"\u01f4\u01f5\u01fa\u0217\u0250\u02a8\u02bb\u02c1\u02d0\u02d1\u0300\u0345\u0360\u0361"
+"\u0386\u038a\u038c\u038c\u038e\u03a1\u03a3\u03ce\u03d0\u03d6\u03da\u03da\u03dc\u03dc"
+"\u03de\u03de\u03e0\u03e0\u03e2\u03f3\u0401\u040c\u040e\u044f\u0451\u045c\u045e\u0481"
+"\u0483\u0486\u0490\u04c4\u04c7\u04c8\u04cb\u04cc\u04d0\u04eb\u04ee\u04f5\u04f8\u04f9"
+"\u0531\u0556\u0559\u0559\u0561\u0586\u0591\u05a1\u05a3\u05b9\u05bb\u05bd\u05bf\u05bf"
+"\u05c1\u05c2\u05c4\u05c4\u05d0\u05ea\u05f0\u05f2\u0621\u063a\u0640\u0652\u0660\u0669"
+"\u0670\u06b7\u06ba\u06be\u06c0\u06ce\u06d0\u06d3\u06d5\u06e8\u06ea\u06ed\u06f0\u06f9"
+"\u0901\u0903\u0905\u0939\u093c\u094d\u0951\u0954\u0958\u0963\u0966\u096f\u0981\u0983"
+"\u0985\u098c\u098f\u0990\u0993\u09a8\u09aa\u09b0\u09b2\u09b2\u09b6\u09b9\u09bc\u09bc"
+"\u09be\u09c4\u09c7\u09c8\u09cb\u09cd\u09d7\u09d7\u09dc\u09dd\u09df\u09e3\u09e6\u09f1"
+"\u0a02\u0a02\u0a05\u0a0a\u0a0f\u0a10\u0a13\u0a28\u0a2a\u0a30\u0a32\u0a33\u0a35\u0a36"
+"\u0a38\u0a39\u0a3c\u0a3c\u0a3e\u0a42\u0a47\u0a48\u0a4b\u0a4d\u0a59\u0a5c\u0a5e\u0a5e"
+"\u0a66\u0a74\u0a81\u0a83\u0a85\u0a8b\u0a8d\u0a8d\u0a8f\u0a91\u0a93\u0aa8\u0aaa\u0ab0"
+"\u0ab2\u0ab3\u0ab5\u0ab9\u0abc\u0ac5\u0ac7\u0ac9\u0acb\u0acd\u0ae0\u0ae0\u0ae6\u0aef"
+"\u0b01\u0b03\u0b05\u0b0c\u0b0f\u0b10\u0b13\u0b28\u0b2a\u0b30\u0b32\u0b33\u0b36\u0b39"
+"\u0b3c\u0b43\u0b47\u0b48\u0b4b\u0b4d\u0b56\u0b57\u0b5c\u0b5d\u0b5f\u0b61\u0b66\u0b6f"
+"\u0b82\u0b83\u0b85\u0b8a\u0b8e\u0b90\u0b92\u0b95\u0b99\u0b9a\u0b9c\u0b9c\u0b9e\u0b9f"
+"\u0ba3\u0ba4\u0ba8\u0baa\u0bae\u0bb5\u0bb7\u0bb9\u0bbe\u0bc2\u0bc6\u0bc8\u0bca\u0bcd"
+"\u0bd7\u0bd7\u0be7\u0bef\u0c01\u0c03\u0c05\u0c0c\u0c0e\u0c10\u0c12\u0c28\u0c2a\u0c33"
+"\u0c35\u0c39\u0c3e\u0c44\u0c46\u0c48\u0c4a\u0c4d\u0c55\u0c56\u0c60\u0c61\u0c66\u0c6f"
+"\u0c82\u0c83\u0c85\u0c8c\u0c8e\u0c90\u0c92\u0ca8\u0caa\u0cb3\u0cb5\u0cb9\u0cbe\u0cc4"
+"\u0cc6\u0cc8\u0cca\u0ccd\u0cd5\u0cd6\u0cde\u0cde\u0ce0\u0ce1\u0ce6\u0cef\u0d02\u0d03"
+"\u0d05\u0d0c\u0d0e\u0d10\u0d12\u0d28\u0d2a\u0d39\u0d3e\u0d43\u0d46\u0d48\u0d4a\u0d4d"
+"\u0d57\u0d57\u0d60\u0d61\u0d66\u0d6f\u0e01\u0e2e\u0e30\u0e3a\u0e40\u0e4e\u0e50\u0e59"
+"\u0e81\u0e82\u0e84\u0e84\u0e87\u0e88\u0e8a\u0e8a\u0e8d\u0e8d\u0e94\u0e97\u0e99\u0e9f"
+"\u0ea1\u0ea3\u0ea5\u0ea5\u0ea7\u0ea7\u0eaa\u0eab\u0ead\u0eae\u0eb0\u0eb9\u0ebb\u0ebd"
+"\u0ec0\u0ec4\u0ec6\u0ec6\u0ec8\u0ecd\u0ed0\u0ed9\u0f18\u0f19\u0f20\u0f29\u0f35\u0f35"
+"\u0f37\u0f37\u0f39\u0f39\u0f3e\u0f47\u0f49\u0f69\u0f71\u0f84\u0f86\u0f8b\u0f90\u0f95"
+"\u0f97\u0f97\u0f99\u0fad\u0fb1\u0fb7\u0fb9\u0fb9\u10a0\u10c5\u10d0\u10f6\u1100\u1100"
+"\u1102\u1103\u1105\u1107\u1109\u1109\u110b\u110c\u110e\u1112\u113c\u113c\u113e\u113e"
+"\u1140\u1140\u114c\u114c\u114e\u114e\u1150\u1150\u1154\u1155\u1159\u1159\u115f\u1161"
+"\u1163\u1163\u1165\u1165\u1167\u1167\u1169\u1169\u116d\u116e\u1172\u1173\u1175\u1175"
+"\u119e\u119e\u11a8\u11a8\u11ab\u11ab\u11ae\u11af\u11b7\u11b8\u11ba\u11ba\u11bc\u11c2"
+"\u11eb\u11eb\u11f0\u11f0\u11f9\u11f9\u1e00\u1e9b\u1ea0\u1ef9\u1f00\u1f15\u1f18\u1f1d"
+"\u1f20\u1f45\u1f48\u1f4d\u1f50\u1f57\u1f59\u1f59\u1f5b\u1f5b\u1f5d\u1f5d\u1f5f\u1f7d"
+"\u1f80\u1fb4\u1fb6\u1fbc\u1fbe\u1fbe\u1fc2\u1fc4\u1fc6\u1fcc\u1fd0\u1fd3\u1fd6\u1fdb"
+"\u1fe0\u1fec\u1ff2\u1ff4\u1ff6\u1ffc\u20d0\u20dc\u20e1\u20e1\u2126\u2126\u212a\u212b"
+"\u212e\u212e\u2180\u2182\u3005\u3005\u3007\u3007\u3021\u302f\u3031\u3035\u3041\u3094"
+"\u3099\u309a\u309d\u309e\u30a1\u30fa\u30fc\u30fe\u3105\u312c\u4e00\u9fa5\uac00\ud7a3"
+"";
private static final String LETTERS =
"\u0041\u005a\u0061\u007a\u00c0\u00d6\u00d8\u00f6\u00f8\u0131\u0134\u013e\u0141\u0148"
+"\u014a\u017e\u0180\u01c3\u01cd\u01f0\u01f4\u01f5\u01fa\u0217\u0250\u02a8\u02bb\u02c1"
+"\u0386\u0386\u0388\u038a\u038c\u038c\u038e\u03a1\u03a3\u03ce\u03d0\u03d6\u03da\u03da"
+"\u03dc\u03dc\u03de\u03de\u03e0\u03e0\u03e2\u03f3\u0401\u040c\u040e\u044f\u0451\u045c"
+"\u045e\u0481\u0490\u04c4\u04c7\u04c8\u04cb\u04cc\u04d0\u04eb\u04ee\u04f5\u04f8\u04f9"
+"\u0531\u0556\u0559\u0559\u0561\u0586\u05d0\u05ea\u05f0\u05f2\u0621\u063a\u0641\u064a"
+"\u0671\u06b7\u06ba\u06be\u06c0\u06ce\u06d0\u06d3\u06d5\u06d5\u06e5\u06e6\u0905\u0939"
+"\u093d\u093d\u0958\u0961\u0985\u098c\u098f\u0990\u0993\u09a8\u09aa\u09b0\u09b2\u09b2"
+"\u09b6\u09b9\u09dc\u09dd\u09df\u09e1\u09f0\u09f1\u0a05\u0a0a\u0a0f\u0a10\u0a13\u0a28"
+"\u0a2a\u0a30\u0a32\u0a33\u0a35\u0a36\u0a38\u0a39\u0a59\u0a5c\u0a5e\u0a5e\u0a72\u0a74"
+"\u0a85\u0a8b\u0a8d\u0a8d\u0a8f\u0a91\u0a93\u0aa8\u0aaa\u0ab0\u0ab2\u0ab3\u0ab5\u0ab9"
+"\u0abd\u0abd\u0ae0\u0ae0\u0b05\u0b0c\u0b0f\u0b10\u0b13\u0b28\u0b2a\u0b30\u0b32\u0b33"
+"\u0b36\u0b39\u0b3d\u0b3d\u0b5c\u0b5d\u0b5f\u0b61\u0b85\u0b8a\u0b8e\u0b90\u0b92\u0b95"
+"\u0b99\u0b9a\u0b9c\u0b9c\u0b9e\u0b9f\u0ba3\u0ba4\u0ba8\u0baa\u0bae\u0bb5\u0bb7\u0bb9"
+"\u0c05\u0c0c\u0c0e\u0c10\u0c12\u0c28\u0c2a\u0c33\u0c35\u0c39\u0c60\u0c61\u0c85\u0c8c"
+"\u0c8e\u0c90\u0c92\u0ca8\u0caa\u0cb3\u0cb5\u0cb9\u0cde\u0cde\u0ce0\u0ce1\u0d05\u0d0c"
+"\u0d0e\u0d10\u0d12\u0d28\u0d2a\u0d39\u0d60\u0d61\u0e01\u0e2e\u0e30\u0e30\u0e32\u0e33"
+"\u0e40\u0e45\u0e81\u0e82\u0e84\u0e84\u0e87\u0e88\u0e8a\u0e8a\u0e8d\u0e8d\u0e94\u0e97"
+"\u0e99\u0e9f\u0ea1\u0ea3\u0ea5\u0ea5\u0ea7\u0ea7\u0eaa\u0eab\u0ead\u0eae\u0eb0\u0eb0"
+"\u0eb2\u0eb3\u0ebd\u0ebd\u0ec0\u0ec4\u0f40\u0f47\u0f49\u0f69\u10a0\u10c5\u10d0\u10f6"
+"\u1100\u1100\u1102\u1103\u1105\u1107\u1109\u1109\u110b\u110c\u110e\u1112\u113c\u113c"
+"\u113e\u113e\u1140\u1140\u114c\u114c\u114e\u114e\u1150\u1150\u1154\u1155\u1159\u1159"
+"\u115f\u1161\u1163\u1163\u1165\u1165\u1167\u1167\u1169\u1169\u116d\u116e\u1172\u1173"
+"\u1175\u1175\u119e\u119e\u11a8\u11a8\u11ab\u11ab\u11ae\u11af\u11b7\u11b8\u11ba\u11ba"
+"\u11bc\u11c2\u11eb\u11eb\u11f0\u11f0\u11f9\u11f9\u1e00\u1e9b\u1ea0\u1ef9\u1f00\u1f15"
+"\u1f18\u1f1d\u1f20\u1f45\u1f48\u1f4d\u1f50\u1f57\u1f59\u1f59\u1f5b\u1f5b\u1f5d\u1f5d"
+"\u1f5f\u1f7d\u1f80\u1fb4\u1fb6\u1fbc\u1fbe\u1fbe\u1fc2\u1fc4\u1fc6\u1fcc\u1fd0\u1fd3"
+"\u1fd6\u1fdb\u1fe0\u1fec\u1ff2\u1ff4\u1ff6\u1ffc\u2126\u2126\u212a\u212b\u212e\u212e"
+"\u2180\u2182\u3007\u3007\u3021\u3029\u3041\u3094\u30a1\u30fa\u3105\u312c\u4e00\u9fa5"
+"\uac00\ud7a3";
private static final String DIGITS =
"\u0030\u0039\u0660\u0669\u06F0\u06F9\u0966\u096F\u09E6\u09EF\u0A66\u0A6F\u0AE6\u0AEF"
+"\u0B66\u0B6F\u0BE7\u0BEF\u0C66\u0C6F\u0CE6\u0CEF\u0D66\u0D6F\u0E50\u0E59\u0ED0\u0ED9"
+"\u0F20\u0F29";
}
msv-2009.1/xsdlib/src-apache/com/sun/msv/datatype/regexp/InternalImpl.java 0000644 0001750 0001750 00000001425 10466722137 026663 0 ustar giovanni giovanni package com.sun.msv.datatype.regexp;
import com.sun.msv.datatype.xsd.regex.RegExp;
import com.sun.msv.datatype.xsd.regex.RegExpFactory;
import java.text.ParseException;
/**
* {@link RegExpFactory} by the internal copy of Xerces.
*
* @author Kohsuke Kawaguchi
*/
public final class InternalImpl extends RegExpFactory {
public RegExp compile(String exp) throws ParseException {
final RegularExpression re;
try {
re = new RegularExpression(exp,"X");
} catch ( com.sun.msv.datatype.regexp.ParseException e ) {
throw new ParseException(e.getMessage(),e.getLocation());
}
return new RegExp() {
public boolean matches(String text) {
return re.matches(text);
}
};
}
}
msv-2009.1/xsdlib/src-apache/com/sun/msv/datatype/regexp/BMPattern.java 0000644 0001750 0001750 00000024246 10223107437 026116 0 ustar giovanni giovanni /*
* The Apache Software License, Version 1.1
*
*
* Copyright (c) 1999-2002 The Apache Software Foundation. All rights
* reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
*
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
*
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in
* the documentation and/or other materials provided with the
* distribution.
*
* 3. The end-user documentation included with the redistribution,
* if any, must include the following acknowledgment:
* "This product includes software developed by the
* Apache Software Foundation (http://www.apache.org/)."
* Alternately, this acknowledgment may appear in the software itself,
* if and wherever such third-party acknowledgments normally appear.
*
* 4. The names "Xerces" and "Apache Software Foundation" must
* not be used to endorse or promote products derived from this
* software without prior written permission. For written
* permission, please contact apache@apache.org.
*
* 5. Products derived from this software may not be called "Apache",
* nor may "Apache" appear in their name, without prior written
* permission of the Apache Software Foundation.
*
* THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESSED OR IMPLIED
* WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
* OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
* DISCLAIMED. IN NO EVENT SHALL THE APACHE SOFTWARE FOUNDATION OR
* ITS CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
* SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
* LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF
* USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
* ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
* OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT
* OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
* SUCH DAMAGE.
* ====================================================================
*
* This software consists of voluntary contributions made by many
* individuals on behalf of the Apache Software Foundation and was
* originally based on software copyright (c) 1999, International
* Business Machines, Inc., http://www.apache.org. For more
* information on the Apache Software Foundation, please see
* .
*/
package com.sun.msv.datatype.regexp;
import java.text.CharacterIterator;
/**
* Boyer-Moore searcher.
*
* @version BMPattern.java,v 1.3 2002/08/09 15:18:17 neilg Exp
*/
final class BMPattern {
char[] pattern;
int[] shiftTable;
boolean ignoreCase;
public BMPattern(String pat, boolean ignoreCase) {
this(pat, 256, ignoreCase);
}
public BMPattern(String pat, int tableSize, boolean ignoreCase) {
this.pattern = pat.toCharArray();
this.shiftTable = new int[tableSize];
this.ignoreCase = ignoreCase;
int length = pattern.length;
for (int i = 0; i < this.shiftTable.length; i ++)
this.shiftTable[i] = length;
for (int i = 0; i < length; i ++) {
char ch = this.pattern[i];
int diff = length-i-1;
int index = ch % this.shiftTable.length;
if (diff < this.shiftTable[index])
this.shiftTable[index] = diff;
if (this.ignoreCase) {
ch = Character.toUpperCase(ch);
index = ch % this.shiftTable.length;
if (diff < this.shiftTable[index])
this.shiftTable[index] = diff;
ch = Character.toLowerCase(ch);
index = ch % this.shiftTable.length;
if (diff < this.shiftTable[index])
this.shiftTable[index] = diff;
}
}
}
/**
*
* @return -1 if iterator does not contain this pattern.
*/
public int matches(CharacterIterator iterator, int start, int limit) {
if (this.ignoreCase) return this.matchesIgnoreCase(iterator, start, limit);
int plength = this.pattern.length;
if (plength == 0) return start;
int index = start+plength;
while (index <= limit) {
int pindex = plength;
int nindex = index+1;
char ch;
do {
if ((ch = iterator.setIndex(--index)) != this.pattern[--pindex])
break;
if (pindex == 0)
return index;
} while (pindex > 0);
index += this.shiftTable[ch % this.shiftTable.length]+1;
if (index < nindex) index = nindex;
}
return -1;
}
/**
*
* @return -1 if str does not contain this pattern.
*/
public int matches(String str, int start, int limit) {
if (this.ignoreCase) return this.matchesIgnoreCase(str, start, limit);
int plength = this.pattern.length;
if (plength == 0) return start;
int index = start+plength;
while (index <= limit) {
//System.err.println("Starts at "+index);
int pindex = plength;
int nindex = index+1;
char ch;
do {
if ((ch = str.charAt(--index)) != this.pattern[--pindex])
break;
if (pindex == 0)
return index;
} while (pindex > 0);
index += this.shiftTable[ch % this.shiftTable.length]+1;
if (index < nindex) index = nindex;
}
return -1;
}
/**
*
* @return -1 if chars does not contain this pattern.
*/
public int matches(char[] chars, int start, int limit) {
if (this.ignoreCase) return this.matchesIgnoreCase(chars, start, limit);
int plength = this.pattern.length;
if (plength == 0) return start;
int index = start+plength;
while (index <= limit) {
//System.err.println("Starts at "+index);
int pindex = plength;
int nindex = index+1;
char ch;
do {
if ((ch = chars[--index]) != this.pattern[--pindex])
break;
if (pindex == 0)
return index;
} while (pindex > 0);
index += this.shiftTable[ch % this.shiftTable.length]+1;
if (index < nindex) index = nindex;
}
return -1;
}
int matchesIgnoreCase(CharacterIterator iterator, int start, int limit) {
int plength = this.pattern.length;
if (plength == 0) return start;
int index = start+plength;
while (index <= limit) {
int pindex = plength;
int nindex = index+1;
char ch;
do {
char ch1 = ch = iterator.setIndex(--index);
char ch2 = this.pattern[--pindex];
if (ch1 != ch2) {
ch1 = Character.toUpperCase(ch1);
ch2 = Character.toUpperCase(ch2);
if (ch1 != ch2 && Character.toLowerCase(ch1) != Character.toLowerCase(ch2))
break;
}
if (pindex == 0)
return index;
} while (pindex > 0);
index += this.shiftTable[ch % this.shiftTable.length]+1;
if (index < nindex) index = nindex;
}
return -1;
}
int matchesIgnoreCase(String text, int start, int limit) {
int plength = this.pattern.length;
if (plength == 0) return start;
int index = start+plength;
while (index <= limit) {
int pindex = plength;
int nindex = index+1;
char ch;
do {
char ch1 = ch = text.charAt(--index);
char ch2 = this.pattern[--pindex];
if (ch1 != ch2) {
ch1 = Character.toUpperCase(ch1);
ch2 = Character.toUpperCase(ch2);
if (ch1 != ch2 && Character.toLowerCase(ch1) != Character.toLowerCase(ch2))
break;
}
if (pindex == 0)
return index;
} while (pindex > 0);
index += this.shiftTable[ch % this.shiftTable.length]+1;
if (index < nindex) index = nindex;
}
return -1;
}
int matchesIgnoreCase(char[] chars, int start, int limit) {
int plength = this.pattern.length;
if (plength == 0) return start;
int index = start+plength;
while (index <= limit) {
int pindex = plength;
int nindex = index+1;
char ch;
do {
char ch1 = ch = chars[--index];
char ch2 = this.pattern[--pindex];
if (ch1 != ch2) {
ch1 = Character.toUpperCase(ch1);
ch2 = Character.toUpperCase(ch2);
if (ch1 != ch2 && Character.toLowerCase(ch1) != Character.toLowerCase(ch2))
break;
}
if (pindex == 0)
return index;
} while (pindex > 0);
index += this.shiftTable[ch % this.shiftTable.length]+1;
if (index < nindex) index = nindex;
}
return -1;
}
/*
public static void main(String[] argv) {
try {
int[] shiftTable = new int[256];
initializeBoyerMoore(argv[0], shiftTable, true);
int o = -1;
CharacterIterator ite = new java.text.StringCharacterIterator(argv[1]);
long start = System.currentTimeMillis();
//for (int i = 0; i < 10000; i ++)
o = searchIgnoreCasesWithBoyerMoore(ite, 0, argv[0], shiftTable);
start = System.currentTimeMillis()-start;
System.out.println("Result: "+o+", Elapsed: "+start);
} catch (Exception ex) {
ex.printStackTrace();
}
}*/
}
msv-2009.1/xsdlib/.cvsignore 0000644 0001750 0001750 00000000027 10242211006 016070 0 ustar giovanni giovanni dist
target
testLog
msv-2009.1/xsdlib/test/ 0000755 0001750 0001750 00000000000 11622453065 015070 5 ustar giovanni giovanni msv-2009.1/xsdlib/test/util/ 0000755 0001750 0001750 00000000000 11622453065 016045 5 ustar giovanni giovanni msv-2009.1/xsdlib/test/util/ResourceChecker.java 0000644 0001750 0001750 00000003271 07671171415 021774 0 ustar giovanni giovanni /*
* @(#)$Id: ResourceChecker.java 1567 2003-06-09 20:50:21Z kk122374 $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package util;
import java.lang.reflect.Field;
import java.lang.reflect.Modifier;
import java.util.Locale;
/**
* checks the existance of message resource.
*
* @author Kohsuke KAWAGUCHI
*/
public class ResourceChecker {
/**
* checks the existance of message resource.
*
* this method utilizes Java reflection to read values of
* "public static final String ERR_*****.
*
* @param prefix
* Fields whose name does not start with this prefix are not tested.
* Can be "".
*/
public static void check( Class cls, String prefix, Checker checker ) throws Exception {
Field[] fields = cls.getDeclaredFields();
for( int i=0; iKohsuke KAWAGUCHI
*/
public interface Checker
{
void check( String propertyName ) throws Exception;
}
msv-2009.1/xsdlib/test/com/ 0000755 0001750 0001750 00000000000 11622453065 015646 5 ustar giovanni giovanni msv-2009.1/xsdlib/test/com/sun/ 0000755 0001750 0001750 00000000000 11622453065 016453 5 ustar giovanni giovanni msv-2009.1/xsdlib/test/com/sun/msv/ 0000755 0001750 0001750 00000000000 11622453065 017260 5 ustar giovanni giovanni msv-2009.1/xsdlib/test/com/sun/msv/datatype/ 0000755 0001750 0001750 00000000000 11622453065 021073 5 ustar giovanni giovanni msv-2009.1/xsdlib/test/com/sun/msv/datatype/xsd/ 0000755 0001750 0001750 00000000000 11622453065 021671 5 ustar giovanni giovanni msv-2009.1/xsdlib/test/com/sun/msv/datatype/xsd/TotalDigitsFacetTest.java 0000644 0001750 0001750 00000003072 07754233577 026607 0 ustar giovanni giovanni /*
* @(#)$Id: TotalDigitsFacetTest.java 1611 2003-11-11 19:24:47Z kohsuke $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.msv.datatype.xsd;
import junit.framework.Test;
import junit.framework.TestCase;
import junit.framework.TestSuite;
/**
* tests TotalDigitsFacet.
*
* @author Kohsuke KAWAGUCHI
*/
public class TotalDigitsFacetTest extends TestCase
{
public TotalDigitsFacetTest( String name ) { super(name); }
public static void main(java.lang.String[] args) {
junit.textui.TestRunner.run(suite());
}
public static Test suite() {
return new TestSuite(TotalDigitsFacetTest.class);
}
public void testCountScale()
{
assertEquals( 1, TotalDigitsFacet.countPrecision("5") );
assertEquals( 3, TotalDigitsFacet.countPrecision("500") );
assertEquals( 6, TotalDigitsFacet.countPrecision("500000") );
assertEquals( 6, TotalDigitsFacet.countPrecision("-500000.000000") );
assertEquals( 2, TotalDigitsFacet.countPrecision("0.05") );
assertEquals( 2, TotalDigitsFacet.countPrecision(".05") );
assertEquals( 3, TotalDigitsFacet.countPrecision("-0.952") );
assertEquals( 3, TotalDigitsFacet.countPrecision("-9.52") );
assertEquals( 3, TotalDigitsFacet.countPrecision("-952") );
assertEquals( 7, TotalDigitsFacet.countPrecision("-9520000") );
}
}
msv-2009.1/xsdlib/test/com/sun/msv/datatype/xsd/SerializationTest.java 0000644 0001750 0001750 00000004731 10223102562 026203 0 ustar giovanni giovanni /*
* @(#)$Id: SerializationTest.java 1650 2005-03-31 23:19:14Z kohsuke $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.msv.datatype.xsd;
import junit.framework.Test;
import junit.framework.TestCase;
import junit.framework.TestSuite;
import java.io.ByteArrayInputStream;
import java.io.ByteArrayOutputStream;
import java.io.ObjectInputStream;
import java.io.ObjectOutputStream;
/**
* tests serialization of datatypes.
*
* @author Kohsuke KAWAGUCHI
*/
public class SerializationTest extends TestCase
{
public SerializationTest( String name ) { super(name); }
public static void main(java.lang.String[] args) {
junit.textui.TestRunner.run(suite());
}
public static Test suite() {
return new TestSuite(SerializationTest.class);
}
// serialize and de-serialize
public Object freezeDry( Object dt ) throws Exception {
ByteArrayOutputStream bos = new ByteArrayOutputStream();
ObjectOutputStream oos = new ObjectOutputStream(bos);
// serialize it
oos.writeObject(dt);
oos.flush();
ByteArrayInputStream bis = new ByteArrayInputStream(bos.toByteArray());
ObjectInputStream ois = new ObjectInputStream(bis);
return ois.readObject();
}
/** test singleton-ness of built-in datatypes. */
public void testSingletonness() throws Exception {
for( int i=0; iKohsuke KAWAGUCHI
*/
public class FractionDigitsFacetTest extends TestCase
{
public FractionDigitsFacetTest( String name ) { super(name); }
public static void main(java.lang.String[] args) {
junit.textui.TestRunner.run(suite());
}
public static Test suite() {
return new TestSuite(FractionDigitsFacetTest.class);
}
public void testCountScale()
{
assertEquals( 0, FractionDigitsFacet.countScale("5.000000000000") );
assertEquals( 0, FractionDigitsFacet.countScale("-95") );
assertEquals( 1, FractionDigitsFacet.countScale("5.9") );
assertEquals( 1, FractionDigitsFacet.countScale("99925.900") );
assertEquals( 5, FractionDigitsFacet.countScale("6.0000400") );
assertEquals( 5, FractionDigitsFacet.countScale("6.0030400") );
}
}
msv-2009.1/xsdlib/test/com/sun/msv/datatype/xsd/datetime/ 0000755 0001750 0001750 00000000000 11622453065 023465 5 ustar giovanni giovanni msv-2009.1/xsdlib/test/com/sun/msv/datatype/xsd/datetime/UtilTest.java 0000644 0001750 0001750 00000006104 10223102562 026073 0 ustar giovanni giovanni /*
* @(#)$Id: UtilTest.java 1650 2005-03-31 23:19:14Z kohsuke $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.msv.datatype.xsd.datetime;
import com.sun.msv.datatype.xsd.Comparator;
import junit.framework.Test;
import junit.framework.TestCase;
import junit.framework.TestSuite;
import java.math.BigInteger;
/**
* tests Util.
*
* @author Kohsuke KAWAGUCHI
*/
public class UtilTest extends TestCase
{
public UtilTest(String testName) { super(testName); }
public static void main(String[] args)
{
junit.textui.TestRunner.run(suite());
}
public static Test suite()
{
return new TestSuite(UtilTest.class);
}
/** Test of objEqual method, of class com.sun.msv.datatype.datetime.Util. */
public void testObjEqual()
{
assertEquals( true, Util.objEqual(null,null) );
assertEquals( false,Util.objEqual(this,null) );
assertEquals( false,Util.objEqual(null,this) );
assertEquals( true, Util.objEqual(this,this) );
assertEquals( true, Util.objEqual("12","12") );
}
/** Test of objHashCode method, of class com.sun.msv.datatype.datetime.Util. */
public void testObjHashCode()
{
assertEquals( this.hashCode(), Util.objHashCode(this) );
assertEquals( Util.objHashCode(null), Util.objHashCode(null) );
}
/** Test of objCompare method, of class com.sun.msv.datatype.datetime.Util. */
public void testObjCompare()
{
assertEquals( Comparator.EQUAL, Util.objCompare(null,null) );
assertEquals( Comparator.LESS, Util.objCompare(new Integer(10), new Integer(20)) );
assertEquals( Comparator.GREATER, Util.objCompare(new Integer(25), new Integer(20)) );
assertEquals( Comparator.UNDECIDABLE,Util.objCompare(null,new Integer(1)) );
assertEquals( Comparator.UNDECIDABLE,Util.objCompare(new Integer(1),null) );
}
/** Test of int2bi method, of class com.sun.msv.datatype.datetime.Util. */
public void testInt2bi()
{
assertEquals( Util.int2bi(15), new BigInteger("15") );
assertEquals( Util.int2bi(new Integer(15)), new BigInteger("15") );
}
/** Test of maximumDayInMonthFor method, of class com.sun.msv.datatype.datetime.Util. */
public void testMaximumDayInMonthFor()
{
int[] test = new int[]{
2000, 0/*Jan*/, 31,
2000, 1/*Feb*/, 29,
1996, 1/*Feb*/, 29,
1900, 1/*Feb*/, 28,
0, 1/*Feb*/, 29,
-400, 1/*Feb*/, 29,
-397, 1/*Feb*/, 28 };
for( int i=0; iKohsuke KAWAGUCHI
*/
public class DateTimeFactoryTest extends TestCase {
public DateTimeFactoryTest(java.lang.String testName) {
super(testName);
}
public static void main(java.lang.String[] args) {
junit.textui.TestRunner.run(suite());
}
public static Test suite() {
return new TestSuite(DateTimeFactoryTest.class);
}
public static void testCreateFromTime()
{
// 1 second
IDateTimeValueType sec1 = DateTimeFactory.
createFromTime(null,null,new Integer(1000),null);
assertEquals( sec1,
new BigDateTimeValueType(null, null, null, null, null, new BigDecimal("1"), null ) );
}
}
msv-2009.1/xsdlib/test/com/sun/msv/datatype/xsd/datetime/BigTimeDurationValueTypeTest.java 0000644 0001750 0001750 00000006572 10223102562 032054 0 ustar giovanni giovanni /*
* @(#)$Id: BigTimeDurationValueTypeTest.java 1650 2005-03-31 23:19:14Z kohsuke $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.msv.datatype.xsd.datetime;
import com.sun.msv.datatype.xsd.Comparator;
import junit.framework.Test;
import junit.framework.TestCase;
import junit.framework.TestSuite;
/**
* tests BigTimeDurationValueType.
*
* @author Kohsuke KAWAGUCHI
*/
public class BigTimeDurationValueTypeTest extends TestCase {
public BigTimeDurationValueTypeTest(String testName) {
super(testName);
}
public static void main(String[] args) {
junit.textui.TestRunner.run(suite());
}
public static Test suite() {
return new TestSuite(BigTimeDurationValueTypeTest.class);
}
private ITimeDurationValueType get( String s ) throws IllegalArgumentException {
return new BigTimeDurationValueType(s);
}
/** Test of hashCode method, of class com.sun.msv.datatype.datetime.BigTimeDurationValueType. */
public void testHashCode() throws Exception
{
assertEquals( get("P400Y").hashCode(), get("P146097D").hashCode() );
assertEquals( get("P1D").hashCode(), get("PT24H").hashCode() );
}
/** Test of compare method, of class com.sun.msv.datatype.datetime.BigTimeDurationValueType. */
public void testCompare() throws Exception
{
assertEquals( get("P1D").compare( get("PT24H") ), Comparator.EQUAL );
assertEquals( get("P1Y").compare( get("P364D") ), Comparator.GREATER );
assertEquals( get("P1Y").compare( get("P365D") ), Comparator.GREATER );
assertEquals( get("P1Y").compare( get("P366D") ), Comparator.LESS );
assertEquals( get("P1Y").compare( get("P367D") ), Comparator.LESS );
assertEquals( get("P1M").compare( get("P27D") ), Comparator.GREATER );
assertEquals( get("P1M").compare( get("P28D") ), Comparator.GREATER );
assertEquals( get("P1M").compare( get("P29D") ), Comparator.UNDECIDABLE );
assertEquals( get("P1M").compare( get("P30D") ), Comparator.UNDECIDABLE );
assertEquals( get("P1M").compare( get("P31D") ), Comparator.LESS );
assertEquals( get("P1M").compare( get("P32D") ), Comparator.LESS );
assertEquals( get("P5M").compare( get("P149D") ), Comparator.GREATER );
assertEquals( get("P5M").compare( get("P150D") ), Comparator.GREATER );
assertEquals( get("P5M").compare( get("P151D") ), Comparator.UNDECIDABLE );
assertEquals( get("P5M").compare( get("P152D") ), Comparator.UNDECIDABLE );
assertEquals( get("P5M").compare( get("P153D") ), Comparator.LESS );
assertEquals( get("P5M").compare( get("P154D") ), Comparator.LESS );
assertEquals( get("P400Y").compare( get("P146097D") ), Comparator.EQUAL );
}
/** Test of getBigValue method, of class com.sun.msv.datatype.datetime.BigTimeDurationValueType. */
public void testGetBigValue() throws Exception
{
ITimeDurationValueType td = get("P153D");
assertSame( td.getBigValue(), td );
}
// /** Test of fromMinutes method, of class com.sun.msv.datatype.datetime.BigTimeDurationValueType. */
/// public void testFromMinutes()
}
msv-2009.1/xsdlib/test/com/sun/msv/datatype/xsd/datetime/TimeDurationFactoryTest.java 0000644 0001750 0001750 00000002106 07671171415 031130 0 ustar giovanni giovanni /*
* @(#)$Id: TimeDurationFactoryTest.java 1567 2003-06-09 20:50:21Z kk122374 $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.msv.datatype.xsd.datetime;
import junit.framework.Test;
import junit.framework.TestCase;
import junit.framework.TestSuite;
/**
* tests TimeDurationFactory.
*
* @author Kohsuke KAWAGUCHI
*/
public class TimeDurationFactoryTest extends TestCase {
public TimeDurationFactoryTest(java.lang.String testName) {
super(testName);
}
public static void main(java.lang.String[] args) {
junit.textui.TestRunner.run(suite());
}
public static Test suite() {
return new TestSuite(TimeDurationFactoryTest.class);
}
/** Test of create method, of class com.sun.msv.datatype.datetime.TimeDurationFactory. */
public void testCreate() {
// TODO: Add your test code here.
}
}
msv-2009.1/xsdlib/test/com/sun/msv/datatype/xsd/datetime/TimeZoneTest.java 0000644 0001750 0001750 00000003343 10223102562 026712 0 ustar giovanni giovanni /*
* @(#)$Id: TimeZoneTest.java 1650 2005-03-31 23:19:14Z kohsuke $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.msv.datatype.xsd.datetime;
import junit.framework.Test;
import junit.framework.TestCase;
import junit.framework.TestSuite;
import java.io.ByteArrayInputStream;
import java.io.ByteArrayOutputStream;
import java.io.ObjectInputStream;
import java.io.ObjectOutputStream;
/**
* tests TimeZone.
*
* @author Kohsuke KAWAGUCHI
*/
public class TimeZoneTest extends TestCase {
public TimeZoneTest(java.lang.String testName) {
super(testName);
}
public static void main(java.lang.String[] args) {
junit.textui.TestRunner.run(suite());
}
public static Test suite() {
return new TestSuite(TimeZoneTest.class);
}
/** serializes o and then returns de-serialized object. */
public Object freezeDry(Object o) throws Exception {
ByteArrayOutputStream bos = new ByteArrayOutputStream();
ObjectOutputStream oos = new ObjectOutputStream(bos);
// serialize it
oos.writeObject(o);
oos.flush();
ByteArrayInputStream bis = new ByteArrayInputStream(bos.toByteArray());
ObjectInputStream ois = new ObjectInputStream(bis);
return ois.readObject();
}
/** test serialization. */
public void testSerialization() throws Exception {
// ensure that serialization doesn't break
assertSame(TimeZone.MISSING, freezeDry(TimeZone.MISSING));
assertSame(TimeZone.ZERO, freezeDry(TimeZone.ZERO));
}
}
msv-2009.1/xsdlib/test/com/sun/msv/datatype/xsd/datetime/BigDateTimeValueTypeTest.java 0000644 0001750 0001750 00000010335 10223102562 031134 0 ustar giovanni giovanni /*
* @(#)$Id: BigDateTimeValueTypeTest.java 1650 2005-03-31 23:19:14Z kohsuke $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.msv.datatype.xsd.datetime;
import com.sun.msv.datatype.xsd.Comparator;
import com.sun.msv.datatype.xsd.DateTimeType;
import com.sun.msv.datatype.xsd.DateType;
import com.sun.msv.datatype.xsd.DurationType;
import com.sun.msv.datatype.xsd.GYearMonthType;
import junit.framework.Test;
import junit.framework.TestCase;
import junit.framework.TestSuite;
/**
* tests BigDateTimeValueType.
*
* @author Kohsuke KAWAGUCHI
*/
public class BigDateTimeValueTypeTest extends TestCase {
public BigDateTimeValueTypeTest(String testName) {
super(testName);
}
public static void main(String[] args) {
junit.textui.TestRunner.run(suite());
}
public static Test suite() {
return new TestSuite(BigDateTimeValueTypeTest.class);
}
/** Test of getBigValue method, of class com.sun.msv.datatype.datetime.BigDateTimeValueType. */
public void testGetBigValue() throws Exception
{
BigDateTimeValueType t = parseYearMonth("2000-01");
assertEquals( t, t.getBigValue() );
}
private BigDateTimeValueType parseYearMonth(String s) {
return (BigDateTimeValueType)
GYearMonthType.theInstance.createValue(s,null);
}
private BigDateTimeValueType parseDateTime( String s ) {
return (BigDateTimeValueType)DateTimeType.theInstance.createValue(s,null);
}
private BigDateTimeValueType parseDate( String s ) {
return (BigDateTimeValueType)DateType.theInstance.createValue(s,null);
}
private BigTimeDurationValueType parseDuration( String s ) {
return (BigTimeDurationValueType)DurationType.theInstance.createValue(s,null);
}
/** Test of compare method, of class com.sun.msv.datatype.datetime.BigDateTimeValueType. */
public void testCompare() throws Exception
{
// from examples of the spec
int r;
r = parseDateTime("2000-01-15T00:00:00").compare(
parseDateTime("2000-02-15T00:00:00") );
assertEquals( r, Comparator.LESS );
r = parseDateTime("2000-01-15T12:00:00" ).compare(
parseDateTime("2000-01-16T12:00:00Z") );
assertEquals( r, Comparator.LESS );
r = parseDateTime("2000-01-01T12:00:00" ).compare(
parseDateTime("1999-12-31T23:00:00Z") );
assertEquals( r, Comparator.UNDECIDABLE );
r = parseDateTime("2000-01-16T12:00:00" ).compare(
parseDateTime("2000-01-16T12:00:00Z") );
assertEquals( r, Comparator.UNDECIDABLE );
r = parseDateTime("2000-01-16T00:00:00" ).compare(
parseDateTime("2000-01-16T12:00:00Z") );
assertEquals( r, Comparator.UNDECIDABLE );
}
/** Test of normalize method, of class com.sun.msv.datatype.datetime.BigDateTimeValueType. */
public void testNormalize() throws Exception
{
IDateTimeValueType v;
v = parseDateTime("2000-03-04T23:00:00-03:00").normalize();
// equals method compares two by calling normalize,
// so actually this cannot be said as a testing.
assertEquals( v, parseDateTime("2000-03-05T02:00:00Z") );
}
/** Test of add method, of class com.sun.msv.datatype.datetime.BigDateTimeValueType. */
public void testAdd() throws Exception
{
BigDateTimeValueType v;
// from examples of Appendix.E of the spec.
v = parseDateTime("2000-01-12T12:13:14Z").add(
parseDuration("P1Y3M5DT7H10M3.3S") ).getBigValue();
assertEquals( v, parseDateTime("2001-04-17T19:23:17.3Z") );
v = parseYearMonth("2000-01").add( parseDuration("-P3M") ).getBigValue();
assertEquals( v, parseYearMonth("1999-10") );
v = parseDate("2000-01-12-05:00").add(
parseDuration("PT33H") ).getBigValue();
assertEquals( v, parseDate("2000-01-13-05:00") );
}
}
msv-2009.1/xsdlib/test/com/sun/msv/datatype/xsd/Const.java 0000644 0001750 0001750 00000002040 07377046733 023632 0 ustar giovanni giovanni package com.sun.msv.datatype.xsd;
public class Const
{
/** all built-in type names. */
public static String[] builtinTypeNames = new String[] {
"anySimpleType",
"duration",
"dateTime",
"time",
"date",
"gYearMonth",
"gYear",
"gMonthDay",
"gDay",
"gMonth",
"string",
"normalizedString",
"token",
"language",
"Name",
"NCName",
"ID",
"IDREF",
"IDREFS",
"ENTITY",
"ENTITIES",
"NMTOKEN",
"NMTOKENS",
"boolean",
"base64Binary",
"hexBinary",
"float",
"decimal",
"integer",
"nonPositiveInteger",
"negativeInteger",
"long",
"int",
"short",
"byte",
"nonNegativeInteger",
"unsignedLong",
"unsignedInt",
"unsignedShort",
"unsignedByte",
"positiveInteger",
"double",
"anyURI",
"QName",
"NOTATION"};
}
msv-2009.1/xsdlib/test/com/sun/msv/datatype/xsd/conformance/ 0000755 0001750 0001750 00000000000 11622453065 024163 5 ustar giovanni giovanni msv-2009.1/xsdlib/test/com/sun/msv/datatype/xsd/conformance/DerivationTest.xml 0000644 0001750 0001750 00000001536 07313753537 027667 0 ustar giovanni giovanni
decimal
msv-2009.1/xsdlib/test/com/sun/msv/datatype/xsd/conformance/TestPatternGenerator.java 0000644 0001750 0001750 00000006016 10223102562 031142 0 ustar giovanni giovanni /*
* @(#)$Id: TestPatternGenerator.java 1650 2005-03-31 23:19:14Z kohsuke $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.msv.datatype.xsd.conformance;
import org.jdom.Element;
import java.util.List;
/**
* parses XML representation of test pattern.
*
* @author Kohsuke KAWAGUCHI
*/
class TestPatternGenerator
{
/**
* parses test pattern specification and returns it.
*
* @param patternElement
* one of "combination","choice","facet".
*/
public static TestPattern parse( Element patternElement )
throws Exception
{
final String tagName = patternElement.getName();
if( tagName.equals("combination") || tagName.equals("choice") )
{
// parse children
List lst = patternElement.getChildren();
TestPattern[] children = new TestPattern[lst.size()];
for( int i=0; iKohsuke KAWAGUCHI
*/
class TestDriver implements ErrorReceiver
{
public static void main (String args[]) throws Exception {
try {
String parser;
if( args.length>=1 ) parser = args[0];
else parser = "org.apache.xerces.parsers.SAXParser";
// reads test case file
Document doc = new SAXBuilder(parser).build(
TestDriver.class.getResourceAsStream("DataTypeTest.xml") );
DataTypeTester tester = new DataTypeTester(System.out,new TestDriver());
// perform test for each "case" item
Iterator itr = doc.getRootElement().getChildren("case").iterator();
while(itr.hasNext())
tester.run( (Element)itr.next() );
} catch(JDOMException e) {
e.printStackTrace();
System.err.println(e.getMessage());
}
}
private DatatypeException getDiagnosis( Datatype dt, String literal ) {
try {
dt.checkValid(literal,DummyContextProvider.theInstance);
return null;
} catch ( DatatypeException de ) {
return de;
}
}
public boolean report( UnexpectedResultException exp ) {
Object o = exp.type.createValue(exp.testInstance,DummyContextProvider.theInstance);
Object jo = exp.type.createJavaObject(exp.testInstance,DummyContextProvider.theInstance);
System.out.println("************* error *************");
System.out.println("type name : "+exp.baseTypeName);
System.out.println("tested instance : \""+exp.testInstance+"\"");
System.out.println("supposed to be valid : "+exp.supposedToBeValid);
System.out.println("verify method : "+exp.type.isValid(exp.testInstance,DummyContextProvider.theInstance) );
System.out.println("createValue method : "+(o!=null) );
System.out.println("createJavaObj method : "+(jo!=null) );
System.out.println("diagnose method : "+(getDiagnosis(exp.type,exp.testInstance)==null) );
System.out.println("JavaObjectType : "+(jo!=null?jo.getClass().toString():"N/A") );
System.out.println("expected Type : "+exp.type.getJavaObjectType() );
if(jo!=null)
try {
System.out.println("serializeJavaObject : "+exp.type.serializeJavaObject(jo,DummyContextProvider.theInstance) );
} catch( Exception e ) {
System.out.println("serializeJavaObject : "+e );
}
if(o!=null)
try {
System.out.println("convertToLexical : "+exp.type.convertToLexicalValue(o,DummyContextProvider.theInstance));
} catch( Exception e ) {
System.out.println("convertToLexical : "+e);
e.printStackTrace();
}
if( exp.incubator.isEmpty() )
System.out.println("facets: none");
else
exp.incubator.dump(System.out);
DatatypeException err = getDiagnosis( exp.type, exp.testInstance );
if( err!=null && err.getMessage()!=null )
System.out.println("diagnosis: " + err.getMessage() );
else
System.out.println("diagnosis: N/A");
// do it again (for trace purpose)
exp.type.isValid(exp.testInstance,DummyContextProvider.theInstance);
return false;
}
public boolean reportTestCaseError( XSDatatype baseType, TypeIncubator incubator, DatatypeException e ) {
/*
System.err.println("---- warning ----");
System.err.println("test case error");
facets.dump(System.err);
System.err.println();
try
{// do it again (for debug)
baseType.derive("anonymous",facets);
}
catch( Exception ee ) { ; }
*/
return false;
}
}
msv-2009.1/xsdlib/test/com/sun/msv/datatype/xsd/conformance/package.html 0000644 0001750 0001750 00000000361 07313753537 026455 0 ustar giovanni giovanni
Conformance Test with XML Schema Part 2 specification.
This suite tests
Does implementation really rejects what it should reject?
Does implementation really accepts what it should accept?
msv-2009.1/xsdlib/test/com/sun/msv/datatype/xsd/conformance/SimpleTestPattern.java 0000644 0001750 0001750 00000003174 10223102562 030447 0 ustar giovanni giovanni /*
* @(#)$Id: SimpleTestPattern.java 1650 2005-03-31 23:19:14Z kohsuke $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.msv.datatype.xsd.conformance;
import com.sun.msv.datatype.xsd.TypeIncubator;
import org.relaxng.datatype.DatatypeException;
/**
* test pattern that corresponds with one test case.
*
* @author Kohsuke KAWAGUCHI
*/
class SimpleTestPattern implements TestPattern
{
/** returns the number of test cases to be generated */
public long totalCases() { return 1; } // pattern itself or the empty
/** restart generating test cases */
public void reset() { idx=0; }
/** get the current test case */
public String get( TypeIncubator incubator ) throws DatatypeException
{
switch(idx)
{
case 0:
incubator.addFacet( facetName, facetValue, false, DummyContextProvider.theInstance );
return answer;
default:
throw new Error();
}
}
/** generate next test case */
public void next() { idx++; }
public boolean hasMore() { return idx!=1; }
private final String facetName;
private final String facetValue;
private final String answer;
private int idx=0;
SimpleTestPattern( String facetName, String facetValue, String answer )
{
this.facetName = facetName;
this.facetValue = facetValue;
this.answer = answer;
reset();
}
}
msv-2009.1/xsdlib/test/com/sun/msv/datatype/xsd/conformance/DataTypeTest.xml 0000644 0001750 0001750 00000110033 07550075712 027262 0 ustar giovanni giovanni
foo:head foo:modbar:role baz:role ascii ooooo:foofoo:not:a:qnameunknown:prefix12345:-joehttp://www.swiftinc.co.jp/ http://www.swiftinc.co.jp/mypage.html#fragment ftp://user:pwd@www.swiftinc.co.jp/?query=a+b-c telnet://192.168.0.1:1234/ip/v4#address http://[FEDC:BA98:7654:3210:FEDC:BA98:7654:3210]:80/index.htmlhttp://[1080:0:0:0:8:800:200C:417A]/index.htmlhttp://[3ffe:2a00:100:7031::1]http://[1080::8:800:200C:417A]/foohttp://[::192.9.5.5]/ipnghttp://[::FFFF:129.144.52.38]:80/index.htmlhttp://[2010:836B:4179::836B:4179]ftp://ftp.is.co.za/rfc/rfc1808.txtgopher://spinaltap.micro.umn.edu/00/Weather/California/Los%20Angeleshttp://www.math.uio.no/faq/compression-faq/part1.htmlmailto:mduerst@ifi.unizh.chnews:comp.infosystems.www.servers.unixtelnet://melvyl.ucop.edu/g:hg./gg//g//gg?y#sg#sg?y#s;xg;xg;x?y#s../..../g../../../../g../../../g../../../../g/./g/../gg..gg....g./../g./g/.g/./hg/../hg;x=1/./yg;x=1/../yg?y/./xg?y/../xg#s/./xg#s/../xhttp:ghttp: x56:-_.!*'();/?:@&=+$, oooo ooooooo oooooo ooooooooo oooooooooo oooooooooo ooooooooo. o123://mydomain.com/ ---01 ---02 ---05 ---28 ---29 ---30 ---31 ---10 ---10-14:00 ---10-08:00 ---10Z ---10+05:00 ---10+09:00 ooooooo oooooo ---10-5:00 10 ---1 ---00 ---32 http://ĥ.gr.jp/" http://ष.gr.jp/" http://⧃.gr.jp/" ooo2001-01-01T00:00:00-14:002001-01-01T00:00:00-02:002001-01-01T00:00:002001-01-01T00:00:00Z2001-01-01T00:00:00+02:002001-01-01T00:00:00+14:009999999999999999999999999-05-13T02:14:00Z2001-01-01T05:12:13.0000000000000000000000000000000000000000000001oooooo oo0000-01-01T12:12:12Z1999-02-29T10:00:00ZP1Y1M1DT1H1M1.1111S-P123YP1YT1Soo oP-123YP5.2DP123YTP52S00:00:0008:00:00Z 12:15:32-08:00 15:00:00Zooo o1:0001:001:00:00-01:00:00 24:00:00 27:00:00 23:59:60 12:60:00--01----02----03----10----11----12----03---07:30--03--Z--03--+00:00--03--+03:00oooooo oooo--00----1----13--5--03-- Z--03--(GMT)--03--(+08:00)--03--+1:00--03--+15:00--03--+12--03--08:00--03---14:01____:_125oo.o..ooo1d2f351234567890abcdefABCDEF ooo 12 34 x5 124ABCXDEFG52==HIJKL1x=AB))((==52==ooooo=A5=q==n===9x5f=tr===onp1qb==en-usEn-Usen-cockneyjp-jamy-own-language en-GB it-can-be-as-long-as-you-wantfroooo oooospace - within-langmorethan-eight-characters-token-mal-formedmal--formednumber-is-NG-1စoridinary stringစဉ more space
tab and returns
oooooo oooridinary stringစဉ more space
tab and returns
oooooo oox--စဉ$#"JPNlamelabellength a b c quickerlength 8GetItDoneMcDonald'sdrive safely more space
tab and returns
oooo oooo ooooooo oo -999999999999999999999999999999999999999999999999999999999999999999Z-10000 -0852+02:00 -0312-0019Z -0002 -0001-09:000001 0001Z 0001-08:00 0001+08:00 0053 0227 12552512Z 7522 9999 12555+09:0099999999999999999999+05:00 999999999999999999999999999999999999999999999999999999999999999999ooooo oooooooo ooooo oo 0000 0000Z 0000+08:00-0000 00000000-00000099 199-1152000ZZ2000+14:012000-14:012000-8:002000+0002000-00:0002000-0:02000 GMT2000z2000-01-01 1 9 9 9 (1999)1999:1999-01999-0013-08-31-0001-12-31 0001-01-01 1996-02-29 2001-01-01 2001-01-01-14:00 2001-01-01-08:00 2001-01-01Z 2001-01-01+05:00 2001-01-01+14:00 2001-01-02 9999999999999999999999999999999999999999999999999999999999999999999-01-01 9999999999999999999999999999999999999999999999999999999999999999999-01-01Z 9999999999999999999999999999999999999999999999999999999999999999999-01-01+05:00 1512-01-04-12:00 1512-01-05+12:00 2000-02-29Zoooo ooooooo ooo ooo 0000-01-01-0000-05-03 00000000-11-04-00000000-07-09 99-05-05 952-03-05 -952-02-09 1253-1-03 1245-09-7 1877- 1- 11932-01-321159-02-291900-02-29Z1168-03-321654-04-31-05:001705-05-321812-06-31+08:000432-07-320779-08-32Z1425-09-311227-10-32-01:001621-11-310015-12-32Z+09:02000-01-01ZZ2000-01-01+14:012000-01-01-14:012000-01-01-8:002000-01-01+0002000-01-01-00:0002000-01-01-0:02000-01-01 GMT2000-01-01z 1956 - 05 - 32 2000/05/05 2000-01-01 Z +05:00truefalse01ooooTrueFALSE-9999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999-123104809034590906573845-9223372036854775809-9223372036854775808-324021378997-2147483649-2147483648-32769-32768-11100-129-128-2-1-00000000000000000000000000000000000000000000000000000000000000+0 1+21271282552561111327673276865535655369089301221474836472147483648429496729442949672954294967296922337203685477580792233720368547758081844674407370955161518446744073709551616999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999990.00..0ooooo ooooo ooooo ooooo ooooo ooooo ooooo ooooo ...ooooo ooooo oooo. ..... ..... ..... ..... ..... ...ooooo ooooo ooooo ooo.. ..... ..... ..... ..... ........ ..... ....o ooooo ooooo ooooo ooooo ooooo ........ ..... ..... ...oo ooooo ooooo ooooo ooooo ......oo ooooo ooooo ooooo ooooo ooooo ooooo o.... ........ .oooo ooooo ooooo ooooo ooooo o.... ..... ........ ...oo ooooo ooooo ooooo o.... ..... ..... ........ ..... .oooo ooooo o.... ..... ..... ..... ........ ..... ....o ooooo ooooo ooooo ooooo ooo.. ........ ..... ....o ooooo ooooo ooooo oooo. ..... ........ ..... ....o ooooo ooooo ooo.. ..... ..... ........ ..... ....o ooooo ooo.. ..... ..... ..... ...ooooo ooooo ooooo ooooo ooooo ooooo ooooo ooooo ooo+-++5+-00x50&h20#x11-1E4-INF-999999999999999999999999999999999999999999999999999999999999999e99999999999999999999999999999999-1.79769313486231570999999999999999999999999999e+308-1.79769313486231570e+308-3.4028234799999999999999E+38f-3.40282347e+38f-.00.000000000000.00000000000e000000000000000000000000000000000.+04.94065645841246544E-3264.94065645841246544E-3240.70119923e-45f0.70119923000000000000000000001e-45f1.40239846e-45fINFNaNoooooo ooooo ooooo oo oooooo ooooo ooooo oo +INFinfInfnan-NaN1e2f0.005d-0.0fE-21e2.50x123 msv-2009.1/xsdlib/test/com/sun/msv/datatype/xsd/conformance/DerivationTester.java 0000644 0001750 0001750 00000000515 07313753537 030333 0 ustar giovanni giovanni /*
* @(#)$Id: DerivationTester.java 789 2001-06-19 22:51:11Z Bear $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.msv.datatype.xsd.conformance;
class DerivationTester
{
}
msv-2009.1/xsdlib/test/com/sun/msv/datatype/xsd/conformance/ErrorReceiver.java 0000644 0001750 0001750 00000001771 10223102562 027577 0 ustar giovanni giovanni /*
* @(#)$Id: ErrorReceiver.java 1650 2005-03-31 23:19:14Z kohsuke $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.msv.datatype.xsd.conformance;
import com.sun.msv.datatype.xsd.TypeIncubator;
import com.sun.msv.datatype.xsd.XSDatatype;
import org.relaxng.datatype.DatatypeException;
/**
* receives conformance test error.
*
* @author Kohsuke KAWAGUCHI
*/
interface ErrorReceiver
{
/**
* when unexpected result is encountered, this method is called
*
* return true to abort test
*/
boolean report( UnexpectedResultException exp );
/**
* when derivation by restriction failed, this method is called
*
* return true to abort test
*/
boolean reportTestCaseError( XSDatatype baseType, TypeIncubator incubator,
DatatypeException e );
}
msv-2009.1/xsdlib/test/com/sun/msv/datatype/xsd/conformance/UnexpectedResultException.java 0000644 0001750 0001750 00000002250 07671171415 032214 0 ustar giovanni giovanni /*
* @(#)$Id: UnexpectedResultException.java 1567 2003-06-09 20:50:21Z kk122374 $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.msv.datatype.xsd.conformance;
import com.sun.msv.datatype.xsd.TypeIncubator;
import com.sun.msv.datatype.xsd.XSDatatype;
/**
* signals unexpected test result.
*
* @author Kohsuke KAWAGUCHI
*/
public class UnexpectedResultException extends Exception
{
public final XSDatatype type;
public final String baseTypeName;
public final String testInstance;
public final boolean supposedToBeValid;
public final TypeIncubator incubator;
UnexpectedResultException( XSDatatype typeObj, String baseTypeName,
String testInstance, boolean supposedToBeValid, TypeIncubator ti )
{
this.type = typeObj;
this.baseTypeName = baseTypeName;
this.testInstance = testInstance;
this.supposedToBeValid = supposedToBeValid;
this.incubator = ti;
}
}
msv-2009.1/xsdlib/test/com/sun/msv/datatype/xsd/conformance/FullCombinationPattern.java 0000644 0001750 0001750 00000007563 10223102562 031451 0 ustar giovanni giovanni /*
* @(#)$Id: FullCombinationPattern.java 1650 2005-03-31 23:19:14Z kohsuke $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.msv.datatype.xsd.conformance;
import com.sun.msv.datatype.xsd.TypeIncubator;
import org.relaxng.datatype.DatatypeException;
/**
* test every possible combination of child patterns.
*
* @author Kohsuke KAWAGUCHI
*/
class FullCombinationPattern implements TestPattern
{
private final TestPattern[] children;
/** True indicates 'AND' mode. False is 'OR' mode. */
private final boolean mergeMode;
private boolean noMore = false;
public FullCombinationPattern( TestPattern[] children, boolean mergeMode )
{
for( int i=0; i 10000
// so if an increment results in carry, reset the digit
// and increment the next digit.
// this's what is done here.
int i;
for( i=children.length-1; i>=0; i-- )
{
children[i].next();
if( children[i].hasMore() )
{
for( i++; iKohsuke KAWAGUCHI
*/
class ChoiceTestPattern implements TestPattern
{
private final TestPattern[] children;
private int idx=0;
public ChoiceTestPattern( TestPattern[] children )
{
this.children = children;
reset();
}
/** returns the number of test cases to be generated */
public long totalCases()
{
int result=0;
for( int i=0; iKohsuke KAWAGUCHI
*/
public class DataTypeTester
{
/** progress indication will be sent to this object */
private final PrintStream out;
/** error will be passed to this object */
private final ErrorReceiver err;
public DataTypeTester( PrintStream out, ErrorReceiver err )
{
this.out = out;
this.err = err;
}
public void run( Element testCase )
throws Exception
{
out.println( testCase.getAttributeValue("name") );
String[] values;
{// read values
List lst = testCase.getChildren("value");
values = new String[lst.size()];
for( int i=0; i");
List lst = wrongs.getChildren("value");
wrongValues = new String[lst.size()];
for( int i=0; iKohsuke KAWAGUCHI
*/
final public class DummyContextProvider implements ValidationContext, SerializationContext
{
private DummyContextProvider() {}
public static final DummyContextProvider theInstance
= new DummyContextProvider();
public String resolveNamespacePrefix( String prefix ) {
if( prefix.equals("foo") )
return "http://foo.examples.com";
if( prefix.equals("bar") || prefix.equals("baz") )
return "http://bar.examples.com";
if( prefix.equals("") || prefix.equals("emp") )
return "http://empty.examples.com";
return null; // undefined
}
public String getNamespacePrefix( String uri ) {
if( uri.equals("http://foo.examples.com") )
return "foo";
if( uri.equals("http://bar.examples.com") )
return "bar";
if( uri.equals("http://empty.examples.com") )
return null; // the default namespace.
return "xyz"; // undefined
}
public boolean isUnparsedEntity( String name ) {
return name.equals("foo") || name.equals("bar");
}
public boolean isNotation( String name ) {
return name.equals("foo") || name.equals("bar");
}
public String getBaseUri() { return null; }
}
msv-2009.1/xsdlib/test/com/sun/msv/datatype/xsd/conformance/TestPattern.java 0000644 0001750 0001750 00000001724 10223102562 027274 0 ustar giovanni giovanni /*
* @(#)$Id: TestPattern.java 1650 2005-03-31 23:19:14Z kohsuke $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.msv.datatype.xsd.conformance;
import com.sun.msv.datatype.xsd.TypeIncubator;
import org.relaxng.datatype.DatatypeException;
/**
* test pattern interface.
*
* @author Kohsuke KAWAGUCHI
*/
public interface TestPattern
{
/** returns the number of test cases to be generated */
long totalCases();
/** restart generating test cases */
void reset();
/** decorate the given TestCase.
*
* @return answer
*/
String get(TypeIncubator ti) throws DatatypeException;
/** generate next test case */
void next();
/** true indicates get method can be safely called */
boolean hasMore();
}
msv-2009.1/xsdlib/test/com/sun/msv/datatype/xsd/DataTypeImplTest.java 0000644 0001750 0001750 00000002623 07671171415 025741 0 ustar giovanni giovanni /*
* @(#)$Id: DataTypeImplTest.java 1567 2003-06-09 20:50:21Z kk122374 $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.msv.datatype.xsd;
import junit.framework.Test;
import junit.framework.TestCase;
import junit.framework.TestSuite;
import util.Checker;
import util.ResourceChecker;
/**
* tests DataTypeImpl.
*
* @author Kohsuke KAWAGUCHI
*/
public class DataTypeImplTest extends TestCase
{
public DataTypeImplTest( String name ) { super(name); }
public static void main(java.lang.String[] args) {
junit.textui.TestRunner.run(suite());
}
public static Test suite() {
return new TestSuite(DataTypeImplTest.class);
}
/** tests the existence of all messages */
public void testMessages() throws Exception {
ResourceChecker.check(
XSDatatypeImpl.class,
"",
new Checker(){
public void check( String propertyName ) {
// if the specified property doesn't exist, this will throw an error
System.out.println(
XSDatatypeImpl.localize(propertyName,new Object[]{"@@@","@@@","@@@","@@@","@@@"}));
}
});
}
}
msv-2009.1/xsdlib/test/com/sun/msv/datatype/xsd/AnyURITypeTest.java 0000644 0001750 0001750 00000003577 07671171415 025366 0 ustar giovanni giovanni /*
* @(#)$Id: AnyURITypeTest.java 1567 2003-06-09 20:50:21Z kk122374 $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.msv.datatype.xsd;
import junit.framework.Test;
import junit.framework.TestCase;
import junit.framework.TestSuite;
/**
* tests AnyURIType.
*
* @author Kohsuke KAWAGUCHI
*/
public class AnyURITypeTest extends TestCase
{
public AnyURITypeTest( String name ) { super(name); }
public static void main(java.lang.String[] args) {
junit.textui.TestRunner.run(suite());
}
public static Test suite() {
return new TestSuite(AnyURITypeTest.class);
}
/** test escaping of ASCII characters */
public void testAsciiEscape()
{
assertEquals( AnyURIType.escape(""), "" );
assertEquals( AnyURIType.escape("ABCXYZ"), "ABCXYZ" );
// those characters may not be escaped.
assertEquals( AnyURIType.escape("-_.!~*'()[]#%"), "-_.!~*'()[]#%" );
// those characters have to be escaped.
assertEquals( AnyURIType.escape(" \""), "%20%22" );
}
/** test %HH escaping of non-ASCII characters. */
public void testNonAsciiEscape()
{
assertEquals( AnyURIType.escape(
new String( new char[]{0x125} ) ),
"%C4%A5" ); // latin small letter h with circumflex
// also known as Planck constant per the speed of light in Physics.
assertEquals( AnyURIType.escape(
new String( new char[]{0x937} ) ),
"%E0%A4%B7" ); // devanagari letter SSA
assertEquals( AnyURIType.escape(
new String( new char[]{0xD8A5,0xDDC3} ) ),
"%F0%A9%97%83" ); // #x295C3
}
}
msv-2009.1/xsdlib/test/com/sun/msv/datatype/xsd/ConcreteTypeTest.java 0000644 0001750 0001750 00000003547 10223102562 025776 0 ustar giovanni giovanni /*
* @(#)$Id: ConcreteTypeTest.java 1650 2005-03-31 23:19:14Z kohsuke $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.msv.datatype.xsd;
import junit.framework.Test;
import junit.framework.TestCase;
import junit.framework.TestSuite;
import java.io.ByteArrayInputStream;
import java.io.ByteArrayOutputStream;
import java.io.ObjectInputStream;
import java.io.ObjectOutputStream;
/**
* tests ConcreteType.
*
* @author Kohsuke KAWAGUCHI
*/
public class ConcreteTypeTest extends TestCase {
public ConcreteTypeTest( String name ) { super(name); }
public static void main(java.lang.String[] args) {
junit.textui.TestRunner.run(suite());
}
public static Test suite() {
return new TestSuite(ConcreteTypeTest.class);
}
/** serializes o and then returns de-serialized object. */
public Object freezeDry( Object o ) throws Exception {
ByteArrayOutputStream bos = new ByteArrayOutputStream();
ObjectOutputStream oos = new ObjectOutputStream(bos);
// serialize it
oos.writeObject( o );
oos.flush();
ByteArrayInputStream bis = new ByteArrayInputStream(bos.toByteArray());
ObjectInputStream ois = new ObjectInputStream(bis);
return ois.readObject();
}
public void testSingleton( Object o ) throws Exception {
assertSame( o, freezeDry(o) );
}
/** test serialization. */
public void testSerialization() throws Exception {
// ensure that serialization doesn't break singleton.
testSingleton( StringType.theInstance );
testSingleton( ByteType.theInstance );
}
}
msv-2009.1/xsdlib/test/com/sun/msv/datatype/xsd/ListTypeTest.java 0000644 0001750 0001750 00000005241 10223102562 025140 0 ustar giovanni giovanni /*
* @(#)$Id: ListTypeTest.java 1650 2005-03-31 23:19:14Z kohsuke $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.msv.datatype.xsd;
import com.sun.msv.datatype.xsd.conformance.DummyContextProvider;
import junit.framework.Test;
import junit.framework.TestCase;
import junit.framework.TestSuite;
import org.relaxng.datatype.DatatypeException;
/**
* tests ListType.
*
* @author Kohsuke KAWAGUCHI
*/
public class ListTypeTest extends TestCase
{
public ListTypeTest( String name ) { super(name); }
public static void main(java.lang.String[] args) {
junit.textui.TestRunner.run(suite());
}
public static Test suite() {
return new TestSuite(ListTypeTest.class);
}
private ListType createList( String newName, XSDatatype itemType ) throws DatatypeException
{
return (ListType)DatatypeFactory.deriveByList("",newName,itemType);
}
private ListType createList( String newName, String itemType ) throws DatatypeException
{
return createList( newName, DatatypeFactory.getTypeByName(itemType) );
}
/** test getVariety method */
public void testGetVariety() throws DatatypeException
{
// list is not an atom
assertEquals( XSDatatype.VARIETY_LIST,
createList( "test", "string" ).getVariety() );
}
/** test verify method */
public void testVerify() throws DatatypeException
{
// this test is naive, and we need further systematic testing.
// but better something than nothing.
XSDatatype t = createList("test","short");
assertTrue( t.isValid(" 12 \t13 \r\n14\n \t 5 99 ",
DummyContextProvider.theInstance ));
assertTrue(!t.isValid(" 51 2 6 fff ",
DummyContextProvider.theInstance ));
assertTrue( t.isValid("", // this should be considered as a length 0 list
DummyContextProvider.theInstance ));
assertTrue( t.isValid(" \t \n ",
DummyContextProvider.theInstance ));
}
/** test convertToObject method */
public void testConvertToObject() throws DatatypeException
{
XSDatatype t = createList("myTest", "string" );
ListValueType v = (ListValueType)
t.createValue(" a b c",DummyContextProvider.theInstance);
assertTrue(v.values.length==3);
assertEquals(v.values[0],"a");
assertEquals(v.values[1],"b");
assertEquals(v.values[2],"c");
}
}
msv-2009.1/xsdlib/test/com/sun/msv/datatype/xsd/FinalComponentTest.java 0000644 0001750 0001750 00000004207 10223102562 026300 0 ustar giovanni giovanni /*
* @(#)$Id: FinalComponentTest.java 1650 2005-03-31 23:19:14Z kohsuke $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.msv.datatype.xsd;
import junit.framework.Test;
import junit.framework.TestCase;
import junit.framework.TestSuite;
import org.relaxng.datatype.DatatypeException;
/**
* tests FinalComponent.
*
* @author Kohsuke KAWAGUCHI
*/
public class FinalComponentTest extends TestCase
{
public FinalComponentTest( String name ) { super(name); }
public static void main(java.lang.String[] args) {
junit.textui.TestRunner.run(suite());
}
public static Test suite() {
return new TestSuite(FinalComponentTest.class);
}
public void testDerivationByRestriction() throws DatatypeException
{
TypeIncubator inc = new TypeIncubator(
new FinalComponent(
StringType.theInstance,
XSDatatype.DERIVATION_BY_RESTRICTION ) );
try
{
inc.derive("test","test");
fail("should throw Exception here");
}
catch( DatatypeException bte ) {;}
}
public void testDerivationByList()
{
try
{
DatatypeFactory.deriveByList("test","test",
new FinalComponent(
StringType.theInstance,
XSDatatype.DERIVATION_BY_LIST )
);
fail("should throw Exception here");
}
catch( DatatypeException bte ) {;}
}
public void testDerivationByUnion()
{
try
{
DatatypeFactory.deriveByUnion("","intermediate",
new XSDatatype[]{
new FinalComponent(
StringType.theInstance,
XSDatatype.DERIVATION_BY_UNION ),
NumberType.theInstance } );
fail("should throw Exception here");
}
catch( DatatypeException bte ) {;}
}
}
msv-2009.1/xsdlib/test/com/sun/msv/datatype/xsd/UnionTypeTest.java 0000644 0001750 0001750 00000006423 10223102562 025320 0 ustar giovanni giovanni /*
* @(#)$Id: UnionTypeTest.java 1650 2005-03-31 23:19:14Z kohsuke $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.msv.datatype.xsd;
import com.sun.msv.datatype.xsd.conformance.DummyContextProvider;
import junit.framework.Test;
import junit.framework.TestCase;
import junit.framework.TestSuite;
import org.relaxng.datatype.DatatypeException;
/**
* tests UnionType.
*
* @author Kohsuke KAWAGUCHI
*/
public class UnionTypeTest extends TestCase
{
public UnionTypeTest( String name ) { super(name); }
public static void main(java.lang.String[] args) {
junit.textui.TestRunner.run(suite());
}
public static Test suite() {
return new TestSuite(UnionTypeTest.class);
}
private UnionType createUnion( String newName,
XSDatatype type1, XSDatatype type2, XSDatatype type3 )
throws DatatypeException
{
return (UnionType)DatatypeFactory.deriveByUnion(
"", newName, new XSDatatypeImpl[]{
(XSDatatypeImpl)type1,
(XSDatatypeImpl)type2,
(XSDatatypeImpl)type3});
}
private UnionType createUnion( String newName,
String type1, String type2, String type3 )
throws DatatypeException
{
return createUnion( newName,
DatatypeFactory.getTypeByName(type1),
DatatypeFactory.getTypeByName(type2),
DatatypeFactory.getTypeByName(type3) );
}
/** test get method */
public void testIsAtomType() throws DatatypeException
{
// union is not an atom
assertEquals( XSDatatype.VARIETY_UNION,
createUnion( "test", "string", "integer", "QName" ).getVariety() );
}
/** test verify method */
public void testVerify() throws DatatypeException
{
// this test is naive, and we need further systematic testing.
// but better something than nothing.
XSDatatype u = createUnion(null,"integer","QName","gYearMonth");
assertTrue( u.isValid("1520",DummyContextProvider.theInstance) );
assertTrue( u.isValid("foo:role",DummyContextProvider.theInstance) );
assertTrue( u.isValid("2000-05",DummyContextProvider.theInstance) );
}
/** test convertToObject method */
public void testConvertToObject() throws DatatypeException
{
XSDatatype tf = DatatypeFactory.getTypeByName("float");
XSDatatype td = DatatypeFactory.getTypeByName("date");
XSDatatype th = DatatypeFactory.getTypeByName("hexBinary");
XSDatatype tu = createUnion("myTest", tf, td, th );
assertEquals(
tu.createValue("2.000",DummyContextProvider.theInstance),
tf.createValue("2.000",DummyContextProvider.theInstance) );
assertEquals(
tu.createValue("2001-02-20",DummyContextProvider.theInstance),
td.createValue("2001-02-20",DummyContextProvider.theInstance) );
assertEquals(
tu.createValue("1f5280",DummyContextProvider.theInstance),
th.createValue("1F5280",DummyContextProvider.theInstance) );
}
}
msv-2009.1/xsdlib/test/com/sun/msv/datatype/xsd/WhiteSpaceProcessorTest.java 0000644 0001750 0001750 00000010410 10223102562 027311 0 ustar giovanni giovanni /*
* @(#)$Id: WhiteSpaceProcessorTest.java 1650 2005-03-31 23:19:14Z kohsuke $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.msv.datatype.xsd;
import junit.framework.Test;
import junit.framework.TestCase;
import junit.framework.TestSuite;
import org.relaxng.datatype.DatatypeException;
import java.io.ByteArrayInputStream;
import java.io.ByteArrayOutputStream;
import java.io.ObjectInputStream;
import java.io.ObjectOutputStream;
/**
* tests WhiteSpaceProcessor.
*
* @author Kohsuke KAWAGUCHI
*/
public class WhiteSpaceProcessorTest extends TestCase
{
public WhiteSpaceProcessorTest( String name ) { super(name); }
public static void main(java.lang.String[] args) {
junit.textui.TestRunner.run(suite());
}
public static Test suite() {
return new TestSuite(WhiteSpaceProcessorTest.class);
}
/** test get method */
public void testGet() throws DatatypeException
{
assertSame( "whitespace in parameter must be allowed",
WhiteSpaceProcessor.get("preserve"),
WhiteSpaceProcessor.get("preserve \t \n \r ")
);
assertSame(
WhiteSpaceProcessor.get("collapse"),
WhiteSpaceProcessor.get(" \r\n collapse \t ")
);
assertSame(
WhiteSpaceProcessor.get("replace"),
WhiteSpaceProcessor.get(" \r\n\r\nreplace") );
try
{
WhiteSpaceProcessor.get("unknown");
fail("should throw exception");
}catch(DatatypeException e){;}
}
/** test behavior of preserve */
public void testPreserve() throws DatatypeException
{
WhiteSpaceProcessor target = WhiteSpaceProcessor.get("preserve");
String[] tests = new String[] {
"test",
" a b c ",
"\r\n \ta bb \t\t c \r\r\n\r " };
for( int i=0; iKohsuke KAWAGUCHI
*/
public class DateTimeBaseTypeTest extends TestCase
{
public DateTimeBaseTypeTest( String name ) { super(name); }
public static void main(java.lang.String[] args) {
junit.textui.TestRunner.run(suite());
}
public static Test suite() {
return new TestSuite(DateTimeBaseTypeTest.class);
}
public void testCreateJavaObject() throws Exception {
Calendar o;
o = (Calendar)DateTimeType.theInstance.createJavaObject(
"2001-01-02T03:04:05.678Z", null );
assertEquals( "2 Jan 2001 03:04:05 GMT", o.getTime().toGMTString() );
assertEquals( 0, o.getTimeZone().getRawOffset() );
assertEquals( 678, o.get(Calendar.MILLISECOND) );
// time zone less.
o = (Calendar)DateTimeType.theInstance.createJavaObject(
"2001-01-02T03:04:05", null );
//
assertSame( com.sun.msv.datatype.xsd.datetime.TimeZone.MISSING,
o.getTimeZone() );
// non-GMT.
// when California (-08:00) is 3 AM, it will be 11AM in Greenwich.
o = (Calendar)DateTimeType.theInstance.createJavaObject(
"2001-01-02T03:04:05.678-08:00", null );
assertEquals( "2 Jan 2001 11:04:05 GMT", o.getTime().toGMTString() );
assertEquals( -8*60*60*1000, o.getTimeZone().getRawOffset() );
// time type.
o = (Calendar)TimeType.theInstance.createJavaObject("08:12:30Z",null);
assertTrue( !o.isSet(Calendar.YEAR) );
assertTrue( !o.isSet(Calendar.MONTH) );
assertTrue( !o.isSet(Calendar.DAY_OF_MONTH) );
assertEquals( 8, o.get(Calendar.HOUR) );
assertEquals( 12, o.get(Calendar.MINUTE) );
assertEquals( 30, o.get(Calendar.SECOND) );
}
}
msv-2009.1/xsdlib/test/com/sun/msv/datatype/xsd/XSDatatypeTest.java 0000644 0001750 0001750 00000015604 10223102562 025415 0 ustar giovanni giovanni /*
* @(#)$Id: XSDatatypeTest.java 1650 2005-03-31 23:19:14Z kohsuke $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.msv.datatype.xsd;
import junit.framework.Test;
import junit.framework.TestCase;
import junit.framework.TestSuite;
import org.relaxng.datatype.DatatypeException;
/**
* tests XSDatatype.
*
* @author Kohsuke KAWAGUCHI
*/
public class XSDatatypeTest extends TestCase
{
public XSDatatypeTest( String name ) { super(name); }
public static void main(java.lang.String[] args) {
junit.textui.TestRunner.run(suite());
}
public static Test suite() {
return new TestSuite(XSDatatypeTest.class);
}
/** test getBaseType method */
public void testGetBaseType() throws DatatypeException {
// check the type hierarchy of the built-in types.
assertTrue( SimpleURType.theInstance==DurationType.theInstance.getBaseType() );
assertTrue( SimpleURType.theInstance==DateTimeType.theInstance.getBaseType() );
assertTrue( SimpleURType.theInstance==TimeType.theInstance.getBaseType() );
assertTrue( SimpleURType.theInstance==DateType.theInstance.getBaseType() );
assertTrue( SimpleURType.theInstance==GYearMonthType.theInstance.getBaseType() );
assertTrue( SimpleURType.theInstance==GYearType.theInstance.getBaseType() );
assertTrue( SimpleURType.theInstance==GMonthDayType.theInstance.getBaseType() );
assertTrue( SimpleURType.theInstance==GDayType.theInstance.getBaseType() );
assertTrue( SimpleURType.theInstance==GMonthType.theInstance.getBaseType() );
assertTrue( SimpleURType.theInstance==BooleanType.theInstance.getBaseType() );
assertTrue( SimpleURType.theInstance==Base64BinaryType.theInstance.getBaseType() );
assertTrue( SimpleURType.theInstance==HexBinaryType.theInstance.getBaseType() );
assertTrue( SimpleURType.theInstance==FloatType.theInstance.getBaseType() );
assertTrue( SimpleURType.theInstance==DoubleType.theInstance.getBaseType() );
assertTrue( SimpleURType.theInstance==AnyURIType.theInstance.getBaseType() );
assertTrue( SimpleURType.theInstance==QnameType.theInstance.getBaseType() );
// NOTATION type
assertTrue( SimpleURType.theInstance==StringType.theInstance.getBaseType() );
assertTrue( SimpleURType.theInstance==NumberType.theInstance.getBaseType() );
assertTrue( StringType.theInstance==NormalizedStringType.theInstance.getBaseType() );
assertTrue( NormalizedStringType.theInstance==TokenType.theInstance.getBaseType() );
assertTrue( TokenType.theInstance==LanguageType.theInstance.getBaseType() );
assertTrue( TokenType.theInstance==NameType.theInstance.getBaseType() );
assertTrue( TokenType.theInstance==NmtokenType.theInstance.getBaseType() );
assertTrue( NameType.theInstance==NcnameType.theInstance.getBaseType() );
assertTrue( NcnameType.theInstance==EntityType.theInstance.getBaseType() );
// ID,IDREF
assertTrue( NumberType.theInstance==IntegerType.theInstance.getBaseType() );
assertTrue( IntegerType.theInstance==NonPositiveIntegerType.theInstance.getBaseType() );
assertTrue( NonPositiveIntegerType.theInstance==NegativeIntegerType.theInstance.getBaseType() );
assertTrue( IntegerType.theInstance==LongType.theInstance.getBaseType() );
assertTrue( LongType.theInstance==IntType.theInstance.getBaseType() );
assertTrue( IntType.theInstance==ShortType.theInstance.getBaseType() );
assertTrue( ShortType.theInstance==ByteType.theInstance.getBaseType() );
assertTrue( IntegerType.theInstance==NonNegativeIntegerType.theInstance.getBaseType() );
assertTrue( NonNegativeIntegerType.theInstance==PositiveIntegerType.theInstance.getBaseType() );
assertTrue( NonNegativeIntegerType.theInstance==UnsignedLongType.theInstance.getBaseType() );
assertTrue( UnsignedLongType.theInstance==UnsignedIntType.theInstance.getBaseType() );
assertTrue( UnsignedIntType.theInstance==UnsignedShortType.theInstance.getBaseType() );
assertTrue( UnsignedShortType.theInstance==UnsignedByteType.theInstance.getBaseType() );
}
/** test isDerivedTypeOf method. */
public void testIsDerivedTypeOf() throws Exception {
XSDatatype urType = SimpleURType.theInstance;
// test reflexivity
assertTrue( NonPositiveIntegerType.theInstance.isDerivedTypeOf(NonPositiveIntegerType.theInstance,true) );
// test multi-step derivation
assertTrue( ByteType.theInstance.isDerivedTypeOf(NumberType.theInstance,true) );
assertTrue( EntityType.theInstance.isDerivedTypeOf(TokenType.theInstance,true) );
assertTrue( EntityType.theInstance.isDerivedTypeOf(urType,true) );
// test the simple ur-type
assertTrue( urType.isDerivedTypeOf(urType,true) );
assertTrue( !urType.isDerivedTypeOf(StringType.theInstance,true) );
assertTrue( UnsignedByteType.theInstance.isDerivedTypeOf(urType,true) );
// test the list derivation
XSDatatype longList = DatatypeFactory.deriveByList("","name", LongType.theInstance );
XSDatatype byteList = DatatypeFactory.deriveByList("","name", ByteType.theInstance );
assertTrue( !byteList.isDerivedTypeOf(longList,true) );
assertTrue( !longList.isDerivedTypeOf(byteList,true) );
assertTrue( byteList.isDerivedTypeOf(urType,true) );
assertTrue( longList.isDerivedTypeOf(urType,true) );
assertTrue( !byteList.isDerivedTypeOf(ByteType.theInstance,true) );
// test the union derivation
XSDatatype union1 = DatatypeFactory.deriveByUnion("","name",
new XSDatatype[]{TokenType.theInstance,LongType.theInstance});
XSDatatype union2 = DatatypeFactory.deriveByUnion("","name",
new XSDatatype[]{union1,longList});
XSDatatype union3;
{
TypeIncubator inc = new TypeIncubator(union2);
inc.addFacet( "enumeration", "52", false, null );
union3 = inc.derive(null,null);
}
assertTrue( union1.isDerivedTypeOf(urType,true) );
assertTrue( ShortType.theInstance.isDerivedTypeOf(union1,true) );
assertTrue( union3.isDerivedTypeOf(urType,true) );
assertTrue( union3.isDerivedTypeOf(union2,true) );
assertTrue( longList.isDerivedTypeOf(union2,true) );
assertTrue( union1.isDerivedTypeOf(union2,true) );
assertTrue( TokenType.theInstance.isDerivedTypeOf(union2,true) );
assertTrue( LongType.theInstance.isDerivedTypeOf(union2,true) );
assertTrue( TokenType.theInstance.isDerivedTypeOf(union3,true) );
}
}
msv-2009.1/xsdlib/examples/ 0000755 0001750 0001750 00000000000 11622453066 015730 5 ustar giovanni giovanni msv-2009.1/xsdlib/examples/CommandLineTester.java 0000644 0001750 0001750 00000007631 10223102562 022143 0 ustar giovanni giovanni /*
* @(#)$Id: CommandLineTester.java 1650 2005-03-31 23:19:14Z kohsuke $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
import com.sun.msv.datatype.xsd.DatatypeFactory;
import com.sun.msv.datatype.xsd.StringType;
import com.sun.msv.datatype.xsd.TypeIncubator;
import com.sun.msv.datatype.xsd.XSDatatype;
import org.relaxng.datatype.DatatypeException;
import java.io.BufferedReader;
import java.io.InputStreamReader;
import java.util.StringTokenizer;
/**
* command-line tester of datatype library.
*
* @author Kohsuke KAWAGUCHI
*/
public class CommandLineTester
{
public static void help()
{
System.out.println(
"base \n" +
" set base type name.\n" +
" this will reset all the facets you've added\n" +
"add \n" +
" add facet\n" +
"test \n" +
" test if the value is accepted by the current base type and facets\n" +
"quit\n"+
" quit this tool"
);
}
public static void main( String args[] )
throws java.io.IOException
{
System.out.println("XML Schema Part 2 command line tool");
final BufferedReader in = new BufferedReader(new InputStreamReader(System.in));
// TypeIncubator is used to "incubate" a type by adding facets.
// constructor accepts the base type instance.
TypeIncubator incubator = new TypeIncubator(StringType.theInstance);
while(true)
{
try
{
System.out.print("-->");
String s = in.readLine();
StringTokenizer tokens = new StringTokenizer(s);
String cmd = tokens.nextToken();
if( cmd.equals("base") )
{
String typeName = tokens.nextToken();
// to obtain a type by name, call this method.
XSDatatype dt = DatatypeFactory.getTypeByName(typeName);
if(dt==null)
{// if the name is not recognized, null is returned.
System.out.println("no such type");
continue;
}
incubator = new TypeIncubator(dt);
continue;
}
if( cmd.equals("add") )
{
String facetName = tokens.nextToken();
String facetValue = tokens.nextToken();
// to add a facet, call add method.
// you MUST supply a valid ValidationContextProvider,
// although this example omits one.
incubator.addFacet( facetName, facetValue, false, null );
continue;
}
if( cmd.equals("test") )
{
String value = tokens.nextToken();
// a type can be derived by derive method.
// the new type contains all facets that were added.
XSDatatype dt = incubator.derive("","anonymous");
// check validity.
if( dt.isValid(value,null) )
// verify method returns true if the value is valid.
System.out.println("valid value");
else
{// it returns false otherwise,
// call diagnose method to see what is wrong.
try
{
dt.checkValid(value,null);
System.out.println("valid");
}
catch( DatatypeException diag )
{
if( diag.getMessage()==null ) {
// datatype object may not support diagnosis.
// in that case, UnsupportedOperationException is thrown.
System.out.println("invalid: no diagnosys available");
} else {
System.out.println("invalid: "+diag.getMessage() );
}
}
}
continue;
}
if( cmd.equals("quit") )
return;
help();
}
catch( DatatypeException bte )
{// this exception happens in cases like:
// 1. unapplicable facet is added ("minInclusive" for string, etc.)
// 2.
System.out.println("DatatypeException: " +bte.getMessage() );
}
catch( java.util.NoSuchElementException nse )
{// error in command line parsing.
System.out.println("???");
help();
}
catch( RuntimeException rte )
{
rte.printStackTrace();
}
}
}
}
msv-2009.1/xsdlib/doc/ 0000755 0001750 0001750 00000000000 11622453065 014656 5 ustar giovanni giovanni msv-2009.1/xsdlib/doc/copyright.txt 0000644 0001750 0001750 00000005265 07626741573 017454 0 ustar giovanni giovanni Copyright 2001-@@YEAR@@ Sun Microsystems, Inc. 901 San Antonio Road, Palo Alto,
California, 94303, U.S.A. All rights reserved.
Sun Microsystems, Inc. has intellectual property rights relating to
technology embodied in this product. In particular, and without
limitation, these intellectual property rights may include one or more
of the U.S. patents listed at http://www.sun.com/patents and one or
more additional patents or pending patent applications in the U.S. and
other countries. This product is distributed under licenses
restricting its use, copying, distribution, and decompilation. No part
of this product may be reproduced in any form by any means without
prior written authorization of Sun and its licensors, if any. Third
party software, including font technology, is copyrighted and licensed
from Sun suppliers. Sun, the Sun logo, and Sun Microsystems are
trademarks or registered trademarks of Sun Microsystems, Inc. in the
U.S. and other countries. This product includes software developed by
the Apache Software Foundation (http://www.apache.org/). Federal
Acquisitions: Commercial Software - Government Users Subject to
Standard License Terms and Conditions.
----------------------------------------------------------------------
Copyright 2001-@@YEAR@@ Sun Microsystems, Inc., 901 San Antonio Road, Palo
Alto, Californie 94303 États-Unis. Tous droits réservés. Distribueé
par des licences qui en restreignent l'utilisation. Sun Microsystems,
Inc. a les droits de propriété intellectuels relatants à la
technologie incorporée dans ce produit. En particulier, et sans la
limitation, ces droits de propriété intellectuels peuvent inclure un
ou plus des brevets américains énumérés à http://www.sun.com/patents
et un ou les brevets plus supplémentaires ou les applications de
brevet en attente dans les Etats Unis et les autres pays. Ce produit
ou document est protégé par un copyright et distribué avec des
licences qui en restreignent l'utilisation, la copie, la distribution,
et la décompilation. Aucune partie de ce produit ou document ne peut
être reproduite sous aucune forme, par quelque moyen que ce soit, sans
l'autorisation préalable et écrite de Sun et de ses bailleurs de
licence, s'il y en a. Le logiciel détenu par des tiers, et qui
comprend la technologie relative aux polices de caractères, est
protégé par un copyright et licencié par des fournisseurs de Sun. Sun,
le logo Sun, Sun Microsystems et sont des marques de fabrique ou des
marques d?pos?es de Sun Microsystems, Inc. aux Etats-Unis et dans
d'autres pays. Ce produit inclut le logiciel développé par la base de
Apache Software Foundation (http://www.apache.org/). L'accord du
gouvernement des États Unis est requis avant l'exportation du produit.
msv-2009.1/xsdlib/doc/HowToUse.html 0000644 0001750 0001750 00000032341 07653275712 017276 0 ustar giovanni giovanni
Using the Sun[TM] XML Datatypes Library
Sun's JavaTM Technology Implementation of XML Schema Part 2
The Sun XML Datatypes Library, Sun's JavaTM technology implementation of XML Schema Part 2, is intended for use with applications that incorporate XML Schema Part 2.
This distribution of the XML Datatypes Library includes a sample class file, src/com/sun/tranquilo/datatype/CommandLineTester.java, which is provided as a guide for implementing your own Java classes with the Datatypes Library.
Introduction: Validating Strings
The following example validates a string with integer datatype. The getTypeByName method lets you obtain a reference to a built-in datatype.
import com.sun.msv.datatype.xsd.XSDatatype;
void f( String v ) {
// obtain a type object
XSDatatype dt = DatatypeFactory.getTypeByName("integer");
// validates a type
if( dt.isValid(v,null) )
; // v is a valid integer
else
; // v is not a valid integer
}
Some datatypes require context information to validate. For example, the QName type, which validates something like prefix:localPart, needs to know that the given prefix is properly declared. This information must be supplied to Datatype object by the caller. To do this, the caller must provide an object that implements the ValidationContext interface and pass it as the second parameter of the verify method.
import org.relaxng.datatype.ValidationContext;
class MyContext implements ValidationContext
{
String resolveNamespacePrefix( String prefix ) {
// resolves namespace prefix to namespace URI.
}
boolean isUnparsedEntity( String entityName ) {
// checks if given name is a valid entity name.
}
...
}
void f( String v, MyContext context ) {
// obtain a type object
XSDatatype dt = DatatypeFactory.getTypeByName("QName");
// validates a type
if( dt.isValid(v,context) )
; // v is a valid QName
else
; // v is not a valid QName
}
When the datatype is "context-dependent", the caller must provide a valid ValidationContext, as in the second example. For other datatypes, the caller can pass null, as in the first example. Use the isContextDependent method to check if a datatype is context dependent or not.
Deriving A New Type
By List
The following example derives a new type from an existing XSDatatype object by list.
The first two parameters specifiy the namespace URI and the local name of the newly created type.
When an error is found during derivation, a org.relaxng.datatype.DatatypeException will be thrown. For example, if you derive a type by list from another list type, an exception will be thrown.
By Union
The following example derives a new type from existing XSDatatype objects by union.
The following example derives a new type by adding facets.
XSDatatype f() throws DatatypeException {
XSDatatype baseType = DatatypeFactory.getTypeByName("string");
// create a type incubator with the base type
TypeIncubator incubator = new TypeIncubator(baseType);
// add facets
incubator.addFacet( "minLength", "5", false, null );
incubator.addFacet( "maxLength", "20", false, null );
// derive a new type by those facets
XSDatatype derived = incubator.derive("","newTypeName");
return derived;
}
The third parameter to the addFacet method specifies whether that facet should be "fixed" or not. Once a facet is fixed, a derived type can no longer restrict that facet.
The fourth parameter is again ValidationContext, which is sometimes necessary (imagine adding an enumeration facet to QName.) The above example does not supply one since we know the base type is a context independent datatype, but in general the caller should supply an object that implements ValidationContext.
DatatypeException can be thrown when you add a facet, or when you call the derive method.
Diagnosing Errors
The following example provides a diagnostic message to users about what is wrong with their value.
In this way, the user gets informative error messages. If the Datatype object does not support diagnosis, the getMessage method returns null. It is the caller's responsibility to handle this situation correctly.
Known Limitations
Types float and double: the spec says a lexical value must be mapped to the closest value in the value space. However, This library cannot accept values that are larger than the maximum value for that type or smaller than the minimum value for that type. This should not be a problem for most users.
ID, IDREF, and IDREFS types are not implemented. Although uniqueness constraints are removed from Part 2, these types are still intended to be used with uniqueness constraints. These constraints are so special that it is impossible to provide a generic implementation. com.sun.tranquilo.datatype.DatatypeFactory does not recognize these three types.
NOTATION type is not implemented. com.sun.tranquilo.datatype.DatatypeFactory does not recognize this type.
length, minLength, and maxLength facets are effectively limited to the value 2147483647. Values above this limit are recognized, but will be treated as this limit. Items larger than this limit will not be validated correctly. This limitation has no practical impact.
Regarding length and min/maxLength facets of anyURI the spec does not define what is the unit of length. This version implements length facet as being in units of XML characters in the lexical space.
Regarding length and min/maxLength facets of QName: again, the specification does not define the unit of length. This version implements length facet as being in units of XML characters in the value space ( # of chars in namespace URI + local part ). Users are strongly discouraged from applying length-related facets to QName type.
anyURI (formerly uriReference) is made to accept several IP v6 addresses like ::192.168.0.1, which are not accepted by the original BNF specified in RFC 2373. This modification should be considered as a "bug fix." Although the BNF specified in RFC 2373 has several other problems, those are not fixed. For example, the current release accepts 1:2:3:4:5:6:7:8:9, which is not a valid IP v6 address.
language type is implemented in accordance with RFC 1766, and language identifiers are treated in a case-insensitive way. XML SchemaPart 2 says that the lexical space of the language type will be as defined in XML1.0 Recommendation 2nd edition, but that production was thrown away in the 2nd edition. Furthermore, the derivation shown inXML Schema Part 2 does not correctly implement the definition given in RFC 1766, so apparently there is a problem in the definition of the language type. However, by making language case-insensitive, it is no longer a derived type of token type.
Regarding base64Binary type, RFC 2045 states that "any characters outside of the base64 alphabet are to be ignored in base64-encoded data." This makes "validation" of base64Binary meaningless. For example, <picture>))))</picture>; is considered as valid base64Binary. Developers should keep this in mind.
minInclusive, maxInclusive, minExclusive, and maxExclusive facets of date/time related types do not work properly. XML Schema Part 2 is broken as regards the order relation of these types. This also affects the behavior of the "enumeration" facet (since equality is a part of order-relation). See Kawaguchi's comments to www-xml-schema-comments@w3.org for details (
[1][2][3] and
[4]
).
msv-2009.1/xsdlib/doc/Apache-LICENSE-1.1.txt 0000644 0001750 0001750 00000005413 07271335007 020160 0 ustar giovanni giovanni /* ====================================================================
* The Apache Software License, Version 1.1
*
* Copyright (c) 2000 The Apache Software Foundation. All rights
* reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
*
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
*
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in
* the documentation and/or other materials provided with the
* distribution.
*
* 3. The end-user documentation included with the redistribution,
* if any, must include the following acknowledgment:
* "This product includes software developed by the
* Apache Software Foundation (http://www.apache.org/)."
* Alternately, this acknowledgment may appear in the software itself,
* if and wherever such third-party acknowledgments normally appear.
*
* 4. The names "Apache" and "Apache Software Foundation" must
* not be used to endorse or promote products derived from this
* software without prior written permission. For written
* permission, please contact apache@apache.org.
*
* 5. Products derived from this software may not be called "Apache",
* nor may "Apache" appear in their name, without prior written
* permission of the Apache Software Foundation.
*
* THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESSED OR IMPLIED
* WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
* OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
* DISCLAIMED. IN NO EVENT SHALL THE APACHE SOFTWARE FOUNDATION OR
* ITS CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
* SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
* LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF
* USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
* ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
* OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT
* OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
* SUCH DAMAGE.
* ====================================================================
*
* This software consists of voluntary contributions made by many
* individuals on behalf of the Apache Software Foundation. For more
* information on the Apache Software Foundation, please see
* .
*
* Portions of this software are based upon public domain software
* originally written at the National Center for Supercomputing Applications,
* University of Illinois, Urbana-Champaign.
*/
msv-2009.1/xsdlib/doc/license.txt 0000644 0001750 0001750 00000003121 11156515606 017040 0 ustar giovanni giovanni Copyright (c) 2002-@@YEAR@@ Sun Microsystems, Inc. All Rights Reserved.
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are
met:
- Redistributions of source code must retain the above copyright
notice, this list of conditions and the following disclaimer.
- Redistribution in binary form must reproduct the above copyright
notice, this list of conditions and the following disclaimer in the
documentation and/or other materials provided with the distribution.
Neither the name of Sun Microsystems, Inc. or the names of
contributors may be used to endorse or promote products derived from
this software without specific prior written permission.
This software is provided "AS IS," without a warranty of any kind. ALL
EXPRESS OR IMPLIED CONDITIONS, REPRESENTATIONS AND WARRANTIES,
INCLUDING ANY IMPLIED WARRANTY OF MERCHANTABILITY, FITNESS FOR A
PARTICULAR PURPOSE OR NON-INFRINGEMENT, ARE HEREBY EXCLUDED. SUN AND
ITS LICENSORS SHALL NOT BE LIABLE FOR ANY DAMAGES OR LIABILITIES
SUFFERED BY LICENSEE AS A RESULT OF OR RELATING TO USE, MODIFICATION
OR DISTRIBUTION OF THE SOFTWARE OR ITS DERIVATIVES. IN NO EVENT WILL
SUN OR ITS LICENSORS BE LIABLE FOR ANY LOST REVENUE, PROFIT OR DATA,
OR FOR DIRECT, INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL OR
PUNITIVE DAMAGES, HOWEVER CAUSED AND REGARDLESS OF THE THEORY OF
LIABILITY, ARISING OUT OF THE USE OF OR INABILITY TO USE SOFTWARE,
EVEN IF SUN HAS BEEN ADVISED OF THE POSSIBILITY OF SUCH DAMAGES.
msv-2009.1/xsdlib/doc/README.txt 0000644 0001750 0001750 00000012415 10233225112 016342 0 ustar giovanni giovanni ======================================================================
README FILE FOR THE SUN XML DATATYPES LIBRARY
version @@VERSION@@
Copyright (c) Sun Microsystems, 2001-@@YEAR@@
Document written by Kohsuke Kawaguchi (kohsuke.kawaguchi@eng.sun.com)
======================================================================
Sun XML Datatypes Library, Sun's Java[tm] technology implementation of
W3C's XML Schema Part 2 (http://www.w3.org/TR/xmlschema-2/), is
intended for use with applications that incorporate XML Schema Part 2.
This preview version implements the recommendation version
(http://www.w3.org/TR/2001/REC-xmlschema-2-20010502/) of the W3C XML
Schema Part 2 Datatype.
This product includes software developed by the Apache Software
Foundation (http://www.apache.org/).
----------------------------------------------------------------------
SAMPLE CODE FILE
----------------------------------------------------------------------
This distribution of the XML Datatypes Library includes a sample class
file, src/com/sun/tranquilo/datatype/CommandLineTester.java, which is
provided as a guide for implementing your own Java classes with the
Datatypes Library.
----------------------------------------------------------------------
LICENSE
----------------------------------------------------------------------
The most of the code is licensed under the BSD license (see
license.txt). The only exception to this is the code taken from Apache,
which is licensed under ASL 1.1 (see Apache-LICENSE-1.1.txt)
In the source tree, the code taken from Apache is hosted in 'src-apache'
so that XSDLib can be built without Apache code if necessary.
----------------------------------------------------------------------
KNOWN LIMITATIONS
----------------------------------------------------------------------
1. Types "float" and "double": the spec says a lexical value must be
mapped to the closest value in the value space. However, This
library cannot accept values that are larger than the maximum value
for that type or smaller than the minimum value for that type. This
should not be a problem for most users.
3. "NOTATION" type validates like the "token" type.
4. "length", "minLength", and "maxLength" facets are effectively
limited to the value 2147483647. Values above this limit are
recognized, but will be treated as this limit. Items larger than
this limit will not be validated correctly. This limitation has no
practical impact.
5. Regarding "length" and "min/maxLength" facets of "anyURI," the spec
does not define what is the unit of length. This version implements
"length" facet as being in units of XML characters in the lexical
space.
6. Regarding "length" and "min/maxLength" facets of "QName," again the
specification does not define the unit of length. This version
implements "length" facet as being in units of XML characters in
the value space ( # of chars in namespace URI + local part ). Users
are strongly discouraged from applying length-related facets to
"QName" type.
7. "anyURI" (formerly "uriReference") is made to accept several IP v6
addresses like "::192.168.0.1," which are not accepted by the
original BNF specified in RFC 2373. This modification should be
considered as a "bug fix." Although the BNF specified in RFC 2373
has several other problems, those are not fixed. For example, the
current release accepts "1:2:3:4:5:6:7:8:9," which is not a valid
IP v6 address.
8. "language" type is implemented in accordance with RFC 1766, and
language identifiers are treated in a case-insensitive way. XML
SchemaPart 2 says that the lexical space of the language type will
be as defined in XML1.0 Recommendation 2nd edition, but that
production was thrown away in the 2nd edition. Furthermore, the
derivation shown inXML Schema Part 2 does not correctly implement
the definition given in RFC 1766, so apparently there is a problem
in the definition of the language type. However, by making
"language" case-insensitive, it is no longer a derived type of
"token" type.
9. Regarding "base64Binary" type, RFC 2045 states that "any characters
outside of the base64 alphabet are to be ignored in base64-encoded
data." This makes "validation" of base64Binary meaningless. For
example, )))) is considered as valid
base64Binary. Developers should keep this in mind.
10. minInclusive, maxInclusive, minExclusive, and maxExclusive facets
of date/time related types do not work properly. XML Schema Part 2
is broken as regards the order relation of these types. This also
affects the behavior of the "enumeration" facet (since equality is
a part of order-relation).
See Kawaguchi's comments to www-xml-schema-comments@w3.org
(http://lists.w3.org/Archives/Public/www-xml-schema-comments/) for
details 1, 2, 3, and 4:
http://lists.w3.org/Archives/Public/www-xml-schema-comments/2001JanMar/0365.html
http://lists.w3.org/Archives/Public/www-xml-schema-comments/2001JanMar/0366.html
http://lists.w3.org/Archives/Public/www-xml-schema-comments/2001JanMar/0367.html
http://lists.w3.org/Archives/Public/www-xml-schema-comments/2001JanMar/0368.html
======================================================================
END OF README
msv-2009.1/xsdlib/MANIFEST.MF 0000644 0001750 0001750 00000000227 07334547105 015550 0 ustar giovanni giovanni Manifest-Version: 1.0
Main-Class: com.sun.msv.datatype.xsd.CommandLineTester
Created-By: 1.2.2 (Sun Microsystems Inc.)
Class-path: relaxngDatatype.jar
msv-2009.1/xsdlib/src/ 0000755 0001750 0001750 00000000000 11622453065 014700 5 ustar giovanni giovanni msv-2009.1/xsdlib/src/com/ 0000755 0001750 0001750 00000000000 11622453065 015456 5 ustar giovanni giovanni msv-2009.1/xsdlib/src/com/sun/ 0000755 0001750 0001750 00000000000 11622453065 016263 5 ustar giovanni giovanni msv-2009.1/xsdlib/src/com/sun/xml/ 0000755 0001750 0001750 00000000000 11622453065 017063 5 ustar giovanni giovanni msv-2009.1/xsdlib/src/com/sun/xml/util/ 0000755 0001750 0001750 00000000000 11622453065 020040 5 ustar giovanni giovanni msv-2009.1/xsdlib/src/com/sun/xml/util/XmlChars.java 0000644 0001750 0001750 00000027404 10233224632 022424 0 ustar giovanni giovanni /*
* @(#)XmlChars.java 1.8 99/01/22
*
* Copyright (c) 1998 Sun Microsystems, Inc. All Rights Reserved.
*/
package com.sun.xml.util;
/**
* Methods in this class are used to determine whether characters may
* appear in certain roles in XML documents. Such methods are used
* both to parse and to create such documents.
*
* @version 1.8
* @author David Brownell
*/
public class XmlChars
{
// can't construct instances
private XmlChars () { }
/**
* Returns true if the argument, a UCS-4 character code, is valid in
* XML documents. Unicode characters fit into the low sixteen
* bits of a UCS-4 character, and pairs of Unicode surrogate
* characters can be combined to encode UCS-4 characters in
* documents containing only Unicode. (The char datatype
* in the Java Programming Language represents Unicode characters,
* including unpaired surrogates.)
*
*
In XML, UCS-4 characters can also be encoded by the use of
* character references such as �, which
* happens to refer to a character that is disallowed in XML documents.
* UCS-4 characters allowed in XML documents can be expressed with
* one or two Unicode characters.
*
* @param ucs4char The 32-bit UCS-4 character being tested.
*/
static public boolean isChar (int ucs4char)
{
// [2] Char ::= #x0009 | #x000A | #x000D
// | [#x0020-#xD7FF]
// ... surrogates excluded!
// | [#xE000-#xFFFD]
// | [#x10000-#x10ffff]
return ((ucs4char >= 0x0020 && ucs4char <= 0xD7FF)
|| ucs4char == 0x000A || ucs4char == 0x0009
|| ucs4char == 0x000D
|| (ucs4char >= 0xE000 && ucs4char <= 0xFFFD)
|| (ucs4char >= 0x10000 && ucs4char <= 0x10ffff));
}
/**
* Returns true if the character is allowed to be a non-initial
* character in names according to the XML recommendation.
* @see #isNCNameChar(char)
* @see #isLetter(char)
*/
public static boolean isNameChar (char c)
{
// [4] NameChar ::= Letter | Digit | '.' | '_' | ':'
// | CombiningChar | Extender
if (isLetter2 (c))
return true;
else if (c == '>')
return false;
else if (c == '.' || c == '-' || c == '_' || c == ':'
|| isExtender (c))
return true;
else
return false;
}
/**
* Returns true if the character is allowed to be a non-initial
* character in unscoped names according to the rules of the XML
* Namespaces proposed recommendation. Except for precluding
* the colon (used to separate names from their scopes) these
* characters are just as allowed by the XML recommendation.
* @see #isNameChar(char)
* @see #isLetter(char)
*/
public static boolean isNCNameChar (char c)
{
// [NC 5] NCNameChar ::= Letter | Digit | '.' | '_'
// | CombiningChar | Extender
return c != ':' && isNameChar (c);
}
/**
* Returns true if the character is allowed where XML supports
* whitespace characters, false otherwise.
*/
public static boolean isSpace (char c)
{
return c == ' ' || c == '\t' || c == '\n' || c == '\r';
}
/*
* NOTE: java.lang.Character.getType() values are:
*
* UNASSIGNED = 0,
*
* UPPERCASE_LETTER = 1, // Lu
* LOWERCASE_LETTER = 2, // Ll
* TITLECASE_LETTER = 3, // Lt
* MODIFIER_LETTER = 4, // Lm
* OTHER_LETTER = 5, // Lo
* NON_SPACING_MARK = 6, // Mn
* ENCLOSING_MARK = 7, // Me
* COMBINING_SPACING_MARK = 8, // Mc
* DECIMAL_DIGIT_NUMBER = 9, // Nd
* LETTER_NUMBER = 10, // Nl
* OTHER_NUMBER = 11, // No
* SPACE_SEPARATOR = 12, // Zs
* LINE_SEPARATOR = 13, // Zl
* PARAGRAPH_SEPARATOR = 14, // Zp
* CONTROL = 15, // Cc
* FORMAT = 16, // Cf
* // 17 reserved for proposed Ci category
* PRIVATE_USE = 18, // Co
* SURROGATE = 19, // Cs
* DASH_PUNCTUATION = 20, // Pd
* START_PUNCTUATION = 21, // Ps
* END_PUNCTUATION = 22, // Pe
* CONNECTOR_PUNCTUATION = 23, // Pc
* OTHER_PUNCTUATION = 24, // Po
* MATH_SYMBOL = 25, // Sm
* CURRENCY_SYMBOL = 26, // Sc
* MODIFIER_SYMBOL = 27, // Sk
* OTHER_SYMBOL = 28; // So
*/
/**
* Returns true if the character is an XML "letter". XML Names must
* start with Letters or a few other characters, but other characters
* in names must only satisfy the isNameChar predicate.
*
* @see #isNameChar(char)
* @see #isNCNameChar(char)
*/
public static boolean isLetter (char c)
{
// [84] Letter ::= BaseChar | Ideographic
// [85] BaseChar ::= ... too much to repeat
// [86] Ideographic ::= ... too much to repeat
//
// Optimize the typical case.
//
if (c >= 'a' && c <= 'z')
return true;
if (c == '/')
return false;
if (c >= 'A' && c <= 'Z')
return true;
//
// Since the tables are too ridiculous to use in code,
// we're using the footnotes here to drive this test.
//
switch (Character.getType (c)) {
// app. B footnote says these are 'name start'
// chars' ...
case Character.LOWERCASE_LETTER: // Ll
case Character.UPPERCASE_LETTER: // Lu
case Character.OTHER_LETTER: // Lo
case Character.TITLECASE_LETTER: // Lt
case Character.LETTER_NUMBER: // Nl
// OK, here we just have some exceptions to check...
return !isCompatibilityChar (c)
// per "5.14 of Unicode", rule out some combiners
&& !(c >= 0x20dd && c <= 0x20e0);
default:
// check for some exceptions: these are "alphabetic"
return ((c >= 0x02bb && c <= 0x02c1)
|| c == 0x0559 || c == 0x06e5 || c == 0x06e6);
}
}
//
// XML 1.0 discourages "compatibility" characters in names; these
// were defined to permit passing through some information stored in
// older non-Unicode character sets. These always have alternative
// representations in Unicode, e.g. using combining chars.
//
private static boolean isCompatibilityChar (char c)
{
// the numerous comparisions here seem unavoidable,
// but the switch can reduce the number which must
// actually be executed.
switch ((c >> 8) & 0x0ff) {
case 0x00:
// ISO Latin/1 has a few compatibility characters
return c == 0x00aa || c == 0x00b5 || c == 0x00ba;
case 0x01:
// as do Latin Extended A and (parts of) B
return (c >= 0x0132 && c <= 0x0133)
|| (c >= 0x013f && c <= 0x0140)
|| c == 0x0149
|| c == 0x017f
|| (c >= 0x01c4 && c <= 0x01cc)
|| (c >= 0x01f1 && c <= 0x01f3) ;
case 0x02:
// some spacing modifiers
return (c >= 0x02b0 && c <= 0x02b8)
|| (c >= 0x02e0 && c <= 0x02e4);
case 0x03:
return c == 0x037a; // Greek
case 0x05:
return c == 0x0587; // Armenian
case 0x0e:
return c >= 0x0edc && c <= 0x0edd; // Laotian
case 0x11:
// big chunks of Hangul Jamo are all "compatibility"
return c == 0x1101
|| c == 0x1104
|| c == 0x1108
|| c == 0x110a
|| c == 0x110d
|| (c >= 0x1113 && c <= 0x113b)
|| c == 0x113d
|| c == 0x113f
|| (c >= 0x1141 && c <= 0x114b)
|| c == 0x114d
|| c == 0x114f
|| (c >= 0x1151 && c <= 0x1153)
|| (c >= 0x1156 && c <= 0x1158)
|| c == 0x1162
|| c == 0x1164
|| c == 0x1166
|| c == 0x1168
|| (c >= 0x116a && c <= 0x116c)
|| (c >= 0x116f && c <= 0x1171)
|| c == 0x1174
|| (c >= 0x1176 && c <= 0x119d)
|| (c >= 0x119f && c <= 0x11a2)
|| (c >= 0x11a9 && c <= 0x11aa)
|| (c >= 0x11ac && c <= 0x11ad)
|| (c >= 0x11b0 && c <= 0x11b6)
|| c == 0x11b9
|| c == 0x11bb
|| (c >= 0x11c3 && c <= 0x11ea)
|| (c >= 0x11ec && c <= 0x11ef)
|| (c >= 0x11f1 && c <= 0x11f8)
;
case 0x20:
return c == 0x207f; // superscript
case 0x21:
return
// various letterlike symbols
c == 0x2102
|| c == 0x2107
|| (c >= 0x210a && c <= 0x2113)
|| c == 0x2115
|| (c >= 0x2118 && c <= 0x211d)
|| c == 0x2124
|| c == 0x2128
|| (c >= 0x212c && c <= 0x212d)
|| (c >= 0x212f && c <= 0x2138)
// most Roman numerals (less 1K, 5K, 10K)
|| (c >= 0x2160 && c <= 0x217f)
;
case 0x30:
// some Hiragana
return c >= 0x309b && c <= 0x309c;
case 0x31:
// all Hangul Compatibility Jamo
return c >= 0x3131 && c <= 0x318e;
case 0xf9:
case 0xfa:
case 0xfb:
case 0xfc:
case 0xfd:
case 0xfe:
case 0xff:
// the whole "compatibility" area is for that purpose!
return true;
default:
// most of Unicode isn't flagged as being for compatibility
return false;
}
}
// guts of isNameChar/isNCNameChar
private static boolean isLetter2 (char c)
{
// [84] Letter ::= BaseChar | Ideographic
// [85] BaseChar ::= ... too much to repeat
// [86] Ideographic ::= ... too much to repeat
// [87] CombiningChar ::= ... too much to repeat
//
// Optimize the typical case.
//
if (c >= 'a' && c <= 'z')
return true;
if (c == '>')
return false;
if (c >= 'A' && c <= 'Z')
return true;
//
// Since the tables are too ridiculous to use in code,
// we're using the footnotes here to drive this test.
//
switch (Character.getType (c)) {
// app. B footnote says these are 'name start'
// chars' ...
case Character.LOWERCASE_LETTER: // Ll
case Character.UPPERCASE_LETTER: // Lu
case Character.OTHER_LETTER: // Lo
case Character.TITLECASE_LETTER: // Lt
case Character.LETTER_NUMBER: // Nl
// ... and these are name characters 'other
// than name start characters'
case Character.COMBINING_SPACING_MARK: // Mc
case Character.ENCLOSING_MARK: // Me
case Character.NON_SPACING_MARK: // Mn
case Character.MODIFIER_LETTER: // Lm
case Character.DECIMAL_DIGIT_NUMBER: // Nd
// OK, here we just have some exceptions to check...
return !isCompatibilityChar (c)
// per "5.14 of Unicode", rule out some combiners
&& !(c >= 0x20dd && c <= 0x20e0);
case Character.FORMAT:
// starting from Unicode 4.0, this is a FORMAT char.
return c==0x06DD;
default:
// added a character ...
// 212E is in the category So, so I don't know why this is
// a BaseChar. But the spec says so.
return c == 0x0387 || c==0x212E;
}
}
private static boolean isExtender (char c)
{
// [89] Extender ::= ...
return c == 0x00b7 || c == 0x02d0 || c == 0x02d1 || c == 0x0387
|| c == 0x0640 || c == 0x0e46 || c == 0x0ec6
|| c == 0x3005 || (c >= 0x3031 && c <= 0x3035)
|| (c >= 0x309d && c <= 0x309e)
|| (c >= 0x30fc && c <= 0x30fe)
;
}
}
msv-2009.1/xsdlib/src/com/sun/msv/ 0000755 0001750 0001750 00000000000 11622453065 017070 5 ustar giovanni giovanni msv-2009.1/xsdlib/src/com/sun/msv/datatype/ 0000755 0001750 0001750 00000000000 11622453065 020703 5 ustar giovanni giovanni msv-2009.1/xsdlib/src/com/sun/msv/datatype/xsd/ 0000755 0001750 0001750 00000000000 11622453066 021502 5 ustar giovanni giovanni msv-2009.1/xsdlib/src/com/sun/msv/datatype/xsd/NegativeIntegerType.java 0000644 0001750 0001750 00000003050 07671171415 026271 0 ustar giovanni giovanni /*
* @(#)$Id: NegativeIntegerType.java 1567 2003-06-09 20:50:21Z kk122374 $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.msv.datatype.xsd;
import org.relaxng.datatype.ValidationContext;
/**
* "negativeInteger" type.
*
* type of the value object is {@link IntegerValueType}.
* See http://www.w3.org/TR/xmlschema-2/#negativeInteger for the spec
*
* v.isNegative is certainly faster than compareTo(ZERO).
* This the sole reason why this class exists at all.
*
* @author Kohsuke KAWAGUCHI
*/
public class NegativeIntegerType extends IntegerType {
public static final NegativeIntegerType theInstance = new NegativeIntegerType();
private NegativeIntegerType() {
super("negativeInteger",createRangeFacet(
NonPositiveIntegerType.theInstance,
null,
IntegerValueType.create("-1")));
}
final public XSDatatype getBaseType() {
return NonPositiveIntegerType.theInstance;
}
public Object _createValue( String lexicalValue, ValidationContext context ) {
Object o = super._createValue(lexicalValue,context);
if(o==null) return null;
final IntegerValueType v = (IntegerValueType)o;
if( !v.isNegative() ) return null;
return v;
}
// serialization support
private static final long serialVersionUID = 1;
}
msv-2009.1/xsdlib/src/com/sun/msv/datatype/xsd/QnameType.java 0000644 0001750 0001750 00000012071 10223102562 024235 0 ustar giovanni giovanni /*
* @(#)$Id: QnameType.java 1650 2005-03-31 23:19:14Z kohsuke $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.msv.datatype.xsd;
import com.sun.msv.datatype.SerializationContext;
import org.relaxng.datatype.ValidationContext;
/**
* "QName" type.
*
* type of the value object is {@link QnameValueType}.
* See http://www.w3.org/TR/xmlschema-2/#QName for the spec.
*
* @author Kohsuke KAWAGUCHI
*/
public class QnameType extends BuiltinAtomicType implements Discrete {
public static final QnameType theInstance = new QnameType();
private QnameType() { super("QName"); }
final public XSDatatype getBaseType() {
return SimpleURType.theInstance;
}
/**
* QName type always returns true. That is, QName is a context-dependent type.
*/
public boolean isContextDependent() {
return true;
}
protected boolean checkFormat( String value, ValidationContext context ) {
// [6] QName ::= (Prefix ':')? LocalPart
// [7] Prefix ::= NCName
// [8] LocalPart ::= NCName
final int first = value.indexOf(':');
// no Prefix, only check LocalPart
if(first <= 0) return XmlNames.isUnqualifiedName(value);
// Prefix exists, check everything
final int last = value.lastIndexOf(':');
if (last != first) return false;
final String prefix = value.substring (0, first);
return XmlNames.isUnqualifiedName(prefix)
&& XmlNames.isUnqualifiedName(value.substring (first + 1))
&& context.resolveNamespacePrefix(prefix)!=null;
}
public Object _createValue( String value, ValidationContext context ) {
String uri,localPart;
// [6] QName ::= (Prefix ':')? LocalPart
// [7] Prefix ::= NCName
// [8] LocalPart ::= NCName
final int first = value.indexOf(':');
if(first <= 0)
{// no Prefix, only check LocalPart
if(!XmlNames.isUnqualifiedName(value)) return null;
uri = context.resolveNamespacePrefix("");
localPart = value;
} else {
// Prefix exists, check everything
final int last = value.lastIndexOf (':');
if (last != first) return null;
final String prefix = value.substring(0, first);
localPart = value.substring(first + 1);
if(!XmlNames.isUnqualifiedName(prefix)
|| !XmlNames.isUnqualifiedName(localPart) )
return null;
uri = context.resolveNamespacePrefix(prefix);
}
if(uri==null) return null;
return new QnameValueType(uri,localPart);
}
public final int isFacetApplicable( String facetName ) {
if( facetName.equals(FACET_PATTERN)
|| facetName.equals(FACET_ENUMERATION)
|| facetName.equals(FACET_WHITESPACE)
|| facetName.equals(FACET_LENGTH)
|| facetName.equals(FACET_MAXLENGTH)
|| facetName.equals(FACET_MINLENGTH)
)
return APPLICABLE;
else
return NOT_ALLOWED;
}
public final int countLength( Object value ) {
QnameValueType v = (QnameValueType)value;
// the spec does not define what is the unit of length.
// TODO: check the update of the spec and modify this if necessary.
return UnicodeUtil.countLength( v.namespaceURI )+
UnicodeUtil.countLength( v.localPart );
}
public String convertToLexicalValue( Object o, SerializationContext context ) {
if(!( o instanceof QnameValueType ))
throw new UnsupportedOperationException();
QnameValueType v = (QnameValueType)o;
return serialize(v.namespaceURI,v.localPart,context);
}
public String serializeJavaObject( Object value, SerializationContext context ) {
if(!(value instanceof String[])) throw new IllegalArgumentException();
String[] input = (String[])value;
if( input.length!=2 ) throw new IllegalArgumentException();
return serialize(input[0],input[1],context);
}
private String serialize( String uri, String local, SerializationContext context ) {
String prefix = context.getNamespacePrefix(uri);
if(prefix==null) return local;
else return prefix+":"+local;
}
public Object _createJavaObject( String literal, ValidationContext context ) {
QnameValueType v = (QnameValueType)createValue(literal,context);
if(v==null) return null;
// return String[2]
else return new String[]{v.namespaceURI,v.localPart};
}
public Class getJavaObjectType() {
return String[].class;
}
// serialization support
private static final long serialVersionUID = 1;
}
msv-2009.1/xsdlib/src/com/sun/msv/datatype/xsd/IDType.java 0000644 0001750 0001750 00000002142 10034315204 023465 0 ustar giovanni giovanni /*
* @(#)$Id: IDType.java 1634 2004-04-05 17:42:28Z kohsuke $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.msv.datatype.xsd;
/**
* very limited 'ID' type of XML Schema Part 2.
*
*
* The cross-reference semantics of the ID/IDREF types must be
* implemented externally. This type by itself does not enforce such a
* constraint.
*
*
* One can call the {@link #getIdType()} method to enforce the cross-reference
* semantics.
*
* @author Kohsuke KAWAGUCHI
*/
public class IDType extends NcnameType {
public static final IDType theInstance = new IDType();
protected IDType() { super("ID"); }
protected Object readResolve() {
// prevent serialization from breaking the singleton.
return theInstance;
}
public int getIdType() { return ID_TYPE_ID; }
// serialization support
private static final long serialVersionUID = 1;
}
msv-2009.1/xsdlib/src/com/sun/msv/datatype/xsd/UnionType.java 0000644 0001750 0001750 00000010140 10223102562 024257 0 ustar giovanni giovanni /*
* @(#)$Id: UnionType.java 1650 2005-03-31 23:19:14Z kohsuke $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.msv.datatype.xsd;
import com.sun.msv.datatype.SerializationContext;
import org.relaxng.datatype.DatatypeException;
import org.relaxng.datatype.ValidationContext;
/**
* union type.
*
* @author Kohsuke KAWAGUCHI
*/
final public class UnionType extends ConcreteType {
/**
* derives a new datatype from atomic datatypes by union
*/
public UnionType( String nsUri, String newTypeName, XSDatatype[] memberTypes ) throws DatatypeException {
super(nsUri,newTypeName);
if(memberTypes.length==0)
throw new DatatypeException(localize(ERR_EMPTY_UNION));
XSDatatypeImpl[] m = new XSDatatypeImpl[memberTypes.length];
System.arraycopy( memberTypes, 0, m, 0, memberTypes.length );
for( int i=0; iKohsuke KAWAGUCHI
*/
public class WhiteSpaceFacet extends DataTypeWithFacet {
WhiteSpaceFacet( String nsUri, String typeName, XSDatatypeImpl baseType, TypeIncubator facets )
throws DatatypeException {
this(nsUri,typeName, baseType,
WhiteSpaceProcessor.get( (String)facets.getFacet(FACET_WHITESPACE)),
facets.isFixed(FACET_WHITESPACE) );
}
WhiteSpaceFacet( String nsUri, String typeName, XSDatatypeImpl baseType,
WhiteSpaceProcessor proc, boolean _isFixed ) throws DatatypeException {
super(nsUri,typeName, baseType, FACET_WHITESPACE, _isFixed,proc);
// loosened facet check
if( baseType.whiteSpace.tightness() > this.whiteSpace.tightness() ) {
XSDatatype d;
d=baseType.getFacetObject(FACET_WHITESPACE);
if(d==null) d = getConcreteType();
throw new DatatypeException( localize(
ERR_LOOSENED_FACET, FACET_WHITESPACE, d.displayName() ));
}
// consistency with minLength/maxLength is checked in XSDatatypeImpl.derive method.
}
protected boolean checkFormat( String content, ValidationContext context ) {
return baseType.checkFormat(content,context);
}
public Object _createValue( String content, ValidationContext context ) {
return baseType._createValue(content,context);
}
/** whiteSpace facet never constrain anything */
protected void diagnoseByFacet(String content, ValidationContext context) {
;
}
// serialization support
private static final long serialVersionUID = 1;
}
msv-2009.1/xsdlib/src/com/sun/msv/datatype/xsd/ErrorType.java 0000644 0001750 0001750 00000003136 10223102562 024267 0 ustar giovanni giovanni /*
* @(#)$Id: ErrorType.java 1650 2005-03-31 23:19:14Z kohsuke $
*
* Copyright 2002 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.msv.datatype.xsd;
import com.sun.msv.datatype.SerializationContext;
import org.relaxng.datatype.ValidationContext;
/**
* A dummy datatype that can be used to recover from errors.
* This datatype accepts any values and any facets.
* The TypeIncubator class also recognizes this class and
* any operation on ErrorType will never cause any error and
* silently return another ErrorType.
*
*
* @author
* Kohsuke Kawaguchi (kohsuke.kawaguchi@sun.com)
*/
public class ErrorType extends BuiltinAtomicType {
public static final ErrorType theInstance = new ErrorType();
protected ErrorType() {
super("error");
}
protected Object _createValue(String content, ValidationContext context) {
return this;
}
protected boolean checkFormat(String literal, ValidationContext context) {
return true;
}
public String convertToLexicalValue(Object valueObject, SerializationContext context)
throws IllegalArgumentException {
return "";
}
public int isFacetApplicable(String facetName) {
return APPLICABLE;
}
public XSDatatype getBaseType() {
return SimpleURType.theInstance;
}
public Class getJavaObjectType() {
return this.getClass();
}
// serialization support
private static final long serialVersionUID = 1;
}
msv-2009.1/xsdlib/src/com/sun/msv/datatype/xsd/FloatType.java 0000644 0001750 0001750 00000006002 10223102562 024236 0 ustar giovanni giovanni /*
* @(#)$Id: FloatType.java 1650 2005-03-31 23:19:14Z kohsuke $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.msv.datatype.xsd;
import com.sun.msv.datatype.SerializationContext;
import org.relaxng.datatype.ValidationContext;
/**
* "float" type.
*
* type of the value object is java.lang.Float.
* See http://www.w3.org/TR/xmlschema-2/#float for the spec
*
* @author Kohsuke KAWAGUCHI
*/
public class FloatType extends FloatingNumberType {
public static final FloatType theInstance = new FloatType();
private FloatType() { super("float"); }
final public XSDatatype getBaseType() {
return SimpleURType.theInstance;
}
public Object _createValue( String lexicalValue, ValidationContext context ) {
return load(lexicalValue);
}
public static Float load( String s ) {
/* Incompatibilities of XML Schema's float "xfloat" and Java's float "jfloat"
* jfloat.valueOf ignores leading and trailing whitespaces,
whereas this is not allowed in xfloat.
* jfloat.valueOf allows "float type suffix" (f, F) to be
appended after float literal (e.g., 1.52e-2f), whereare
this is not the case of xfloat.
gray zone
---------
* jfloat allows ".523". And there is no clear statement that mentions
this case in xfloat. Although probably this is allowed.
*
*/
try {
if(s.equals("NaN")) return new Float(Float.NaN);
if(s.equals("INF")) return new Float(Float.POSITIVE_INFINITY);
if(s.equals("-INF")) return new Float(Float.NEGATIVE_INFINITY);
if(s.length()==0
|| !isDigitOrPeriodOrSign(s.charAt(0))
|| !isDigitOrPeriodOrSign(s.charAt(s.length()-1)) )
return null;
// these screening process is necessary due to the wobble of Float.valueOf method
return Float.valueOf(s);
} catch( NumberFormatException e ) {
return null;
}
}
public Class getJavaObjectType() {
return Float.class;
}
public String convertToLexicalValue( Object value, SerializationContext context ) {
if(!(value instanceof Float ))
throw new IllegalArgumentException();
return save( (Float)value );
}
public static String save( Float value ) {
float v = value.floatValue();
if( v==Float.NaN ) return "NaN";
if( v==Float.POSITIVE_INFINITY ) return "INF";
if( v==Float.NEGATIVE_INFINITY ) return "-INF";
return value.toString();
}
// serialization support
private static final long serialVersionUID = 1;
}
msv-2009.1/xsdlib/src/com/sun/msv/datatype/xsd/SimpleURType.java 0000644 0001750 0001750 00000003756 10223102562 024706 0 ustar giovanni giovanni /*
* @(#)$Id: SimpleURType.java 1650 2005-03-31 23:19:14Z kohsuke $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.msv.datatype.xsd;
import com.sun.msv.datatype.SerializationContext;
import org.relaxng.datatype.ValidationContext;
/**
* simple "ur-type" type.
*
* type of the value object is java.lang.String.
* See http://www.w3.org/TR/xmlschema-1/#simple-ur-type-itself for the spec
*
* @author Kohsuke KAWAGUCHI
*/
public class SimpleURType extends BuiltinAtomicType {
public static final SimpleURType theInstance = new SimpleURType();
protected SimpleURType() {
super("anySimpleType",WhiteSpaceProcessor.thePreserve);
}
/**
* SimpleURType always returns null to indicate that
* there is no base type for this type.
*/
final public XSDatatype getBaseType() {
return null;
}
/**
* simple ur-type accepts anything.
*/
protected final boolean checkFormat( String content, ValidationContext context ) {
return true;
}
/**
* the value object of the simple ur-type is the lexical value itself.
*/
public Object _createValue( String lexicalValue, ValidationContext context ) {
return lexicalValue;
}
public Class getJavaObjectType() {
return String.class;
}
public String convertToLexicalValue( Object value, SerializationContext context ) {
if( value instanceof String )
return (String)value;
else
throw new IllegalArgumentException();
}
/**
* no facet is applicable to the simple ur-type.
*/
public final int isFacetApplicable( String facetName ) {
return APPLICABLE;
}
// serialization support
private static final long serialVersionUID = 1;
}
msv-2009.1/xsdlib/src/com/sun/msv/datatype/xsd/ngimpl/ 0000755 0001750 0001750 00000000000 11622453066 022770 5 ustar giovanni giovanni msv-2009.1/xsdlib/src/com/sun/msv/datatype/xsd/ngimpl/DatatypeBuilderImpl.java 0000644 0001750 0001750 00000002676 10223102562 027536 0 ustar giovanni giovanni package com.sun.msv.datatype.xsd.ngimpl;
import com.sun.msv.datatype.xsd.TypeIncubator;
import com.sun.msv.datatype.xsd.XSDatatype;
import com.sun.msv.datatype.xsd.XSDatatypeImpl;
import org.relaxng.datatype.Datatype;
import org.relaxng.datatype.DatatypeBuilder;
import org.relaxng.datatype.DatatypeException;
import org.relaxng.datatype.ValidationContext;
class DatatypeBuilderImpl implements DatatypeBuilder {
private TypeIncubator incubator;
DatatypeBuilderImpl( XSDatatype baseType ) {
incubator = new TypeIncubator(baseType);
}
public void addParameter( String name, String value, ValidationContext context )
throws DatatypeException {
if( name.equals(XSDatatype.FACET_ENUMERATION) )
// the enumeration facet is not allowed for RELAX NG.
throw new DatatypeException(
XSDatatypeImpl.localize(XSDatatypeImpl.ERR_NOT_APPLICABLE_FACET, name) );
incubator.addFacet( name, value, false, context );
if( name.equals(XSDatatype.FACET_PATTERN) )
// if the pattern facet is specified, we have to
// derive a new type so that multiple pattern facets can
// work as ANDing.
incubator = new TypeIncubator(incubator.derive(null,null));
}
public Datatype createDatatype() throws DatatypeException {
return incubator.derive(null,null);
}
}
msv-2009.1/xsdlib/src/com/sun/msv/datatype/xsd/ngimpl/DataTypeLibraryImpl.java 0000644 0001750 0001750 00000003042 10223102562 027500 0 ustar giovanni giovanni /*
* @(#)$Id: DataTypeLibraryImpl.java 1650 2005-03-31 23:19:14Z kohsuke $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.msv.datatype.xsd.ngimpl;
import com.sun.msv.datatype.xsd.DatatypeFactory;
import com.sun.msv.datatype.xsd.XSDatatype;
import org.relaxng.datatype.Datatype;
import org.relaxng.datatype.DatatypeBuilder;
import org.relaxng.datatype.DatatypeException;
import org.relaxng.datatype.DatatypeLibrary;
import org.relaxng.datatype.DatatypeLibraryFactory;
/**
* DatatypeLibrary implementation for Sun XML Datatypes Library.
*
* @author Kohsuke KAWAGUCHI
*/
public class DataTypeLibraryImpl implements DatatypeLibrary, DatatypeLibraryFactory {
public Datatype createDatatype( String typeName ) throws DatatypeException {
return getType(typeName);
}
private XSDatatype getType( String typeName) throws DatatypeException {
return DatatypeFactory.getTypeByName(typeName);
}
public DatatypeBuilder createDatatypeBuilder( String typeName ) throws DatatypeException {
return new DatatypeBuilderImpl( getType(typeName) );
}
public DatatypeLibrary createDatatypeLibrary( String uri ) {
if( uri.equals("http://www.w3.org/2001/XMLSchema")
|| uri.equals("http://www.w3.org/2001/XMLSchema-datatypes"))
return this;
return null;
}
}
msv-2009.1/xsdlib/src/com/sun/msv/datatype/xsd/BooleanType.java 0000644 0001750 0001750 00000004631 10223102562 024556 0 ustar giovanni giovanni /*
* @(#)$Id: BooleanType.java 1650 2005-03-31 23:19:14Z kohsuke $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.msv.datatype.xsd;
import com.sun.msv.datatype.SerializationContext;
import org.relaxng.datatype.ValidationContext;
/**
* "boolean" type.
*
* type of the value object is java.lang.Boolean.
* See http://www.w3.org/TR/xmlschema-2/#boolean for the spec
*
* @author Kohsuke KAWAGUCHI
*/
public class BooleanType extends BuiltinAtomicType {
public static final BooleanType theInstance = new BooleanType();
private BooleanType() { super("boolean"); }
final public XSDatatype getBaseType() {
return SimpleURType.theInstance;
}
protected boolean checkFormat( String content, ValidationContext context ) {
return "true".equals(content) || "false".equals(content)
|| "0".equals(content) || "1".equals(content);
}
public Object _createValue( String lexicalValue, ValidationContext context ) {
// for string, lexical space is value space by itself
return load(lexicalValue);
}
public static Boolean load( String s ) {
if( s.equals("true") ) return Boolean.TRUE;
if( s.equals("1") ) return Boolean.TRUE;
if( s.equals("0") ) return Boolean.FALSE;
if( s.equals("false") ) return Boolean.FALSE;
return null;
}
public String convertToLexicalValue( Object value, SerializationContext context ) {
if( value instanceof Boolean )
return save( (Boolean)value );
else
throw new IllegalArgumentException();
}
public static String save( Boolean b ) {
if( b.booleanValue()==true ) return "true";
else return "false";
}
public int isFacetApplicable( String facetName ) {
if(facetName.equals(FACET_PATTERN)
|| facetName.equals(FACET_ENUMERATION)
|| facetName.equals(FACET_WHITESPACE))
return APPLICABLE;
return NOT_ALLOWED;
}
public Class getJavaObjectType() {
return Boolean.class;
}
// serialization support
private static final long serialVersionUID = 1;
}
msv-2009.1/xsdlib/src/com/sun/msv/datatype/xsd/HexBinaryType.java 0000644 0001750 0001750 00000006306 10223102562 025071 0 ustar giovanni giovanni /*
* @(#)$Id: HexBinaryType.java 1650 2005-03-31 23:19:14Z kohsuke $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.msv.datatype.xsd;
import com.sun.msv.datatype.SerializationContext;
import org.relaxng.datatype.ValidationContext;
/**
* "hexBinary" type.
*
* type of the value object is {@link BinaryValueType}.
* See http://www.w3.org/TR/xmlschema-2/#hexBinary for the spec
*
* @author Kohsuke KAWAGUCHI
*/
public class HexBinaryType extends BinaryBaseType {
public static final HexBinaryType theInstance = new HexBinaryType();
private HexBinaryType() { super("hexBinary"); }
// hex decoder
//====================================
private static int hexToBin( char ch ) {
if( '0'<=ch && ch<='9' ) return ch-'0';
if( 'A'<=ch && ch<='F' ) return ch-'A'+10;
if( 'a'<=ch && ch<='f' ) return ch-'a'+10;
return -1;
}
public Object _createValue( String lexicalValue, ValidationContext context ) {
byte[] buf = load(lexicalValue);
if(buf==null) return null;
else return new BinaryValueType(buf);
}
public static byte[] load( String s ) {
final int len = s.length();
// "111" is not a valid hex encoding.
if( len%2 != 0 ) return null;
byte[] out = new byte[len/2];
for( int i=0; i>4) );
r.append( encode(data[i]&0xF) );
}
return r.toString();
}
public String convertToLexicalValue( Object value, SerializationContext context ) {
if(!(value instanceof BinaryValueType))
throw new IllegalArgumentException();
return serializeJavaObject( ((BinaryValueType)value).rawData, context );
}
public static char encode( int ch ) {
ch &= 0xF;
if( ch<10 ) return (char)('0'+ch);
else return (char)('A'+(ch-10));
}
// serialization support
private static final long serialVersionUID = 1;
}
msv-2009.1/xsdlib/src/com/sun/msv/datatype/xsd/GYearMonthType.java 0000644 0001750 0001750 00000001632 10034315204 025211 0 ustar giovanni giovanni /*
* @(#)$Id: GYearMonthType.java 1634 2004-04-05 17:42:28Z kohsuke $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.msv.datatype.xsd;
/**
* "gYearMonth" type.
*
* type of the value object is {@link com.sun.msv.datatype.xsd.datetime.IDateTimeValueType}.
* See http://www.w3.org/TR/xmlschema-2/#gYearMonth for the spec
*
* @author Kohsuke KAWAGUCHI
*/
public class GYearMonthType extends DateTimeBaseType {
public static final GYearMonthType theInstance = new GYearMonthType();
private GYearMonthType() { super("gYearMonth"); }
protected final String getFormat() {
return "%Y-%M%z";
}
// serialization support
private static final long serialVersionUID = 1;
}
msv-2009.1/xsdlib/src/com/sun/msv/datatype/xsd/ShortType.java 0000644 0001750 0001750 00000003203 07671171415 024310 0 ustar giovanni giovanni /*
* @(#)$Id: ShortType.java 1567 2003-06-09 20:50:21Z kk122374 $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.msv.datatype.xsd;
import org.relaxng.datatype.ValidationContext;
/**
* "short" type.
*
* type of the value object is java.lang.Short.
* See http://www.w3.org/TR/xmlschema-2/#short for the spec
*
* @author Kohsuke KAWAGUCHI
*/
public class ShortType extends IntegerDerivedType {
public static final ShortType theInstance =
new ShortType("short",createRangeFacet(IntType.theInstance,
new Short(Short.MIN_VALUE),
new Short(Short.MAX_VALUE)));
protected ShortType(String typeName,XSDatatypeImpl baseFacets) {
super(typeName,baseFacets);
}
public XSDatatype getBaseType() {
return IntType.theInstance;
}
public Object _createValue( String lexicalValue, ValidationContext context ) {
return load(lexicalValue);
}
public static Short load( String s ) {
// Implementation of JDK1.2.2/JDK1.3 is suitable enough
try {
return new Short(removeOptionalPlus(s));
} catch( NumberFormatException e ) {
return null;
}
}
public static String save( Short v ) {
return v.toString();
}
public Class getJavaObjectType() {
return Short.class;
}
// serialization support
private static final long serialVersionUID = 1;
}
msv-2009.1/xsdlib/src/com/sun/msv/datatype/xsd/IntegerType.java 0000644 0001750 0001750 00000004376 10223102562 024602 0 ustar giovanni giovanni /*
* @(#)$Id: IntegerType.java 1650 2005-03-31 23:19:14Z kohsuke $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.msv.datatype.xsd;
import org.relaxng.datatype.DatatypeException;
import org.relaxng.datatype.ValidationContext;
import java.math.BigInteger;
/**
* "integer" type.
*
* type of the value object is {@link IntegerValueType}.
* See http://www.w3.org/TR/xmlschema-2/#integer for the spec
*
* @author Kohsuke KAWAGUCHI
*/
public class IntegerType extends IntegerDerivedType {
/** Singleton instance. */
public static final IntegerType theInstance;
static {
try {
theInstance = new IntegerType("integer",
new FractionDigitsFacet(null,null,NumberType.theInstance,0,true) );
} catch( DatatypeException e ) {
throw new InternalError(); // assertion failure
}
}
protected IntegerType(String typeName,XSDatatypeImpl baseFacets) {
super(typeName,baseFacets);
}
public XSDatatype getBaseType() {
return NumberType.theInstance;
}
public Object _createValue( String lexicalValue, ValidationContext context ) {
return IntegerValueType.create(lexicalValue);
}
public Object _createJavaObject( String literal, ValidationContext context ) {
IntegerValueType o = (IntegerValueType)_createValue(literal,context);
if(o==null) return null;
return new BigInteger(o.toString());
}
public static BigInteger load( String s ) {
IntegerValueType o = IntegerValueType.create(s);
if(o==null) return null;
return new BigInteger(o.toString());
}
public static String save( BigInteger v ) {
return v.toString();
}
// the default implementation of the serializeJavaObject method works correctly.
// so there is no need to override it here.
public Class getJavaObjectType() {
return BigInteger.class;
}
// serialization support
private static final long serialVersionUID = 1;
}
msv-2009.1/xsdlib/src/com/sun/msv/datatype/xsd/PatternFacet.java 0000644 0001750 0001750 00000007733 10223107437 024731 0 ustar giovanni giovanni /*
* @(#)$Id: PatternFacet.java 1652 2005-04-01 00:00:31Z kohsuke $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.msv.datatype.xsd;
import com.sun.msv.datatype.xsd.regex.RegExp;
import com.sun.msv.datatype.xsd.regex.RegExpFactory;
import org.relaxng.datatype.DatatypeException;
import org.relaxng.datatype.ValidationContext;
import java.io.IOException;
import java.io.ObjectInputStream;
import java.util.Vector;
import java.text.ParseException;
/**
* "pattern" facet validator
*
* "pattern" is a constraint facet which is applied against lexical space.
* See http://www.w3.org/TR/xmlschema-2/#dt-pattern for the spec
*
* @author Kohsuke KAWAGUCHI
*/
public final class PatternFacet extends DataTypeWithLexicalConstraintFacet {
/**
* actual object that performs regular expression validation.
* one of the item has to match.
*
* Don't serialize so that we won't have hard-coded dependency to
* a particular regexp lib.
*/
private transient RegExp[] exps;
public RegExp[] getRegExps() { return exps; }
/**
* string representations of the above RegularExpressions.
* this representation is usually human friendly than
* the one generated by RegularExpression.toString method.
*/
final public String[] patterns;
public PatternFacet( String nsUri, String typeName, XSDatatypeImpl baseType, TypeIncubator facets )
throws DatatypeException {
super( nsUri, typeName, baseType, FACET_PATTERN, facets.isFixed(FACET_PATTERN) );
// TODO : am I supposed to implement my own regexp validator?
// at this time, I use Xerces' one.
Vector regExps = facets.getVector(FACET_PATTERN);
patterns = (String[]) regExps.toArray(new String[regExps.size()]);
try {
compileRegExps();
} catch( ParseException pe ) {
// in case regularExpression is not a correct pattern
throw new DatatypeException( localize( ERR_PARSE_ERROR,
pe.getMessage() ) );
}
}
/** Compiles all the regular expressions. */
private void compileRegExps() throws ParseException {
exps = new RegExp[patterns.length];
RegExpFactory factory = RegExpFactory.createFactory();
for(int i=0;iKohsuke KAWAGUCHI
*/
public class NonPositiveIntegerType extends IntegerType {
public static final NonPositiveIntegerType theInstance = new NonPositiveIntegerType();
private NonPositiveIntegerType() {
super("nonPositiveInteger",createRangeFacet(
IntegerType.theInstance,
null,
IntegerValueType.create("0")));
}
final public XSDatatype getBaseType() {
return IntegerType.theInstance;
}
public Object _createValue( String lexicalValue, ValidationContext context ) {
Object o = super._createValue(lexicalValue,context);
if(o==null) return null;
final IntegerValueType v = (IntegerValueType)o;
if( !v.isNonPositive() ) return null;
return v;
}
// serialization support
private static final long serialVersionUID = 1;
}
msv-2009.1/xsdlib/src/com/sun/msv/datatype/xsd/datetime/ 0000755 0001750 0001750 00000000000 11622453066 023276 5 ustar giovanni giovanni msv-2009.1/xsdlib/src/com/sun/msv/datatype/xsd/datetime/ITimeDurationValueType.java 0000644 0001750 0001750 00000001241 07671171415 030517 0 ustar giovanni giovanni /*
* @(#)$Id: ITimeDurationValueType.java 1567 2003-06-09 20:50:21Z kk122374 $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.msv.datatype.xsd.datetime;
/**
* interface as a value type of TimeDurationType
*
* @author Kohsuke KAWAGUCHI
*/
public interface ITimeDurationValueType extends java.io.Serializable {
BigTimeDurationValueType getBigValue();
/** compare two ITimeDurationValueType as defined in
* com.sun.msv.datatype/Comparator
*/
int compare( ITimeDurationValueType rhs );
}
msv-2009.1/xsdlib/src/com/sun/msv/datatype/xsd/datetime/PreciseCalendarParser.java 0000644 0001750 0001750 00000004372 07767675635 030377 0 ustar giovanni giovanni /*
* @(#)$Id: PreciseCalendarParser.java 1623 2003-12-16 21:39:41Z kohsuke $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.msv.datatype.xsd.datetime;
import java.math.BigDecimal;
import java.math.BigInteger;
/**
*
*
* @author
* Kohsuke Kawaguchi (kohsuke.kawaguchi@sun.com)
*/
public class PreciseCalendarParser extends AbstractCalendarParser {
public static BigDateTimeValueType parse( String format, String value ) throws IllegalArgumentException {
PreciseCalendarParser parser = new PreciseCalendarParser(format,value);
parser.parse();
return parser.createCalendar();
}
private PreciseCalendarParser( String format, String value ) {
super(format,value);
}
private BigDateTimeValueType createCalendar() {
return new BigDateTimeValueType(year,month,day,hour,minute,second,timeZone);
}
private BigInteger year;
private Integer month;
private Integer day;
private Integer hour;
private Integer minute;
private BigDecimal second;
private java.util.TimeZone timeZone;
protected void parseFractionSeconds() {
int s = vidx;
BigInteger bi = parseBigInteger(1,Integer.MAX_VALUE);
BigDecimal d = new BigDecimal(bi,vidx-s);
if( second==null) second = d;
else second = second.add(d);
}
protected void setTimeZone(java.util.TimeZone tz) {
if(tz==TimeZone.MISSING) tz=null;
this.timeZone = tz;
}
protected void setSeconds(int i) {
BigDecimal d = new BigDecimal(BigInteger.valueOf(i));
if( second==null) second = d;
else second = second.add(d);
}
protected void setMinutes(int i) {
minute = new Integer(i);
}
protected void setHours(int i) {
hour = new Integer(i);
}
protected void setDay(int i) {
day = new Integer(i-1); // zero origin
}
protected void setMonth(int i) {
month = new Integer(i-1); // zero origin
}
protected void setYear(int i) {
year = BigInteger.valueOf(i);
}
}
msv-2009.1/xsdlib/src/com/sun/msv/datatype/xsd/datetime/PreciseCalendarFormatter.java 0000644 0001750 0001750 00000006421 10012531343 031037 0 ustar giovanni giovanni /*
* @(#)$Id: PreciseCalendarFormatter.java 1630 2004-02-11 22:55:31Z kohsuke $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.msv.datatype.xsd.datetime;
import java.math.BigDecimal;
import java.math.BigInteger;
import java.util.Calendar;
/**
*
*
* @author
* Kohsuke Kawaguchi (kohsuke.kawaguchi@sun.com)
*/
public class PreciseCalendarFormatter extends AbstractCalendarFormatter {
private PreciseCalendarFormatter() {} // no instanciation
private static final PreciseCalendarFormatter theInstance = new PreciseCalendarFormatter();
public static String format( String format, IDateTimeValueType cal ) {
return theInstance.doFormat(format,cal.getBigValue());
}
protected Calendar toCalendar(Object cal) {
return ((BigDateTimeValueType)cal).toCalendar();
}
protected void formatYear(Object cal, StringBuffer buf) {
BigDateTimeValueType bv = ((IDateTimeValueType)cal).getBigValue();
BigInteger year = bv.getYear();
if(year==null) {
buf.append("0000");
return;
}
String s;
if (year.signum() <= 0) {
// negative value
buf.append('-');
s = year.negate().add(BigInteger.ONE).toString();
} else
// positive value
s = year.toString();
while (s.length() < 4)
s = "0" + s;
buf.append(s);
}
protected void formatMonth(Object cal, StringBuffer buf) {
BigDateTimeValueType bv = ((IDateTimeValueType)cal).getBigValue();
formatTwoDigits(bv.getMonth(),1,buf);
}
protected void formatDays(Object cal, StringBuffer buf) {
BigDateTimeValueType bv = ((IDateTimeValueType)cal).getBigValue();
formatTwoDigits(bv.getDay(),1,buf);
}
protected void formatHours(Object cal, StringBuffer buf) {
BigDateTimeValueType bv = ((IDateTimeValueType)cal).getBigValue();
formatTwoDigits(bv.getHour(),buf);
}
protected void formatMinutes(Object cal, StringBuffer buf) {
BigDateTimeValueType bv = ((IDateTimeValueType)cal).getBigValue();
formatTwoDigits(bv.getMinute(),buf);
}
protected void formatSeconds(Object cal, StringBuffer buf) {
BigDateTimeValueType bv = ((IDateTimeValueType)cal).getBigValue();
BigDecimal sec = bv.getSecond();
if (sec == null) {
buf.append("00");
return;
}
// truncate unnecesary 0s.
while( sec.scale()>0 && sec.toString().endsWith("0") )
sec = sec.movePointLeft(1);
String s = sec.toString();
if (sec.compareTo(new java.math.BigDecimal("10")) < 0)
s = "0" + s;
buf.append(s);
}
private void formatTwoDigits(Integer v,StringBuffer buf) {
formatTwoDigits(v,0,buf);
}
/** formats Integer into two-character-wide string. */
private void formatTwoDigits(Integer v, int offset,StringBuffer buf) {
if (v == null)
buf.append("00");
else
formatTwoDigits(v.intValue() + offset,buf);
}
}
msv-2009.1/xsdlib/src/com/sun/msv/datatype/xsd/datetime/.cvsignore 0000644 0001750 0001750 00000000236 07255464013 025300 0 ustar giovanni giovanni ISO8601Parser.java
ISO8601ParserConstants.java
ISO8601ParserTokenManager.java
ASCII_CharStream.java
Token.java
TokenMgrError.java
*.class
ParseException.java
msv-2009.1/xsdlib/src/com/sun/msv/datatype/xsd/datetime/TimeZone.java 0000644 0001750 0001750 00000004773 07767675635 025735 0 ustar giovanni giovanni /*
* @(#)$Id: TimeZone.java 1623 2003-12-16 21:39:41Z kohsuke $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.msv.datatype.xsd.datetime;
import java.io.Serializable;
import java.util.SimpleTimeZone;
/**
* simple time zone component.
*
* @author Kohsuke KAWAGUCHI
*/
public class TimeZone implements java.io.Serializable {
/**
* Difference from GMT in terms of minutes.
* @deprecated here just for the serialization backward compatibility.
*/
public int minutes;
private Object readResolve() {
// use java.util.TimeZone instead
return new SimpleTimeZone(minutes*60*1000,"");
}
/**
* The {@link java.util.TimeZone} representation that corresponds
* to the ZERO singleton instance. Once again, using a special
* instance is a hack to make the round-tripping work OK.
*/
public static final java.util.TimeZone ZERO = new JavaZeroTimeZone();
/**
* The {@link java.util.TimeZone} representation that corresponds
* to the missing time zone.
*/
public static final java.util.TimeZone MISSING = new JavaMissingTimeZone();
// serialization support
private static final long serialVersionUID = 1;
//
// nested inner classes
//
/**
* @deprecated
* exists just for the backward serialization compatibility.
*/
static class ZeroTimeZone extends TimeZone {
ZeroTimeZone() {
}
protected Object readResolve() {
// use the singleton instance
return ZERO;
}
// serialization support
private static final long serialVersionUID = 1;
}
private static class JavaZeroTimeZone extends SimpleTimeZone implements Serializable {
JavaZeroTimeZone() {
super(0, "XSD 'Z' timezone");
}
protected Object readResolve() {
return ZERO;
}
// serialization support
private static final long serialVersionUID = 1;
}
private static class JavaMissingTimeZone extends SimpleTimeZone implements Serializable {
JavaMissingTimeZone() {
super(0, "XSD missing timezone");
}
protected Object readResolve() {
return MISSING;
}
// serialization support
private static final long serialVersionUID = 1;
}
}
msv-2009.1/xsdlib/src/com/sun/msv/datatype/xsd/datetime/CalendarParser.java 0000644 0001750 0001750 00000003760 10046731350 027027 0 ustar giovanni giovanni /*
* @(#)$Id: CalendarParser.java 1639 2004-05-07 16:01:44Z kohsuke $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.msv.datatype.xsd.datetime;
import java.util.Calendar;
import java.util.GregorianCalendar;
/**
* Parses XML Schema date/time related types into {@link java.util.Calendar}.
*
* @author
* Kohsuke Kawaguchi (kohsuke.kawaguchi@sun.com)
*/
public final class CalendarParser extends AbstractCalendarParser {
public static GregorianCalendar parse( String format, String value ) throws IllegalArgumentException {
CalendarParser parser = new CalendarParser(format,value);
parser.parse();
return parser.cal;
}
// this version is faster than new GregorianCalendar()
// which involves in setting the current time.
private final GregorianCalendar cal = new GregorianCalendar(0,0,0);
private CalendarParser( String format, String value ) {
super(format,value);
// erase all the fields to remove any trace of the current time.
cal.clear(Calendar.YEAR);
cal.clear(Calendar.MONTH);
cal.clear(Calendar.DAY_OF_MONTH);
}
protected void parseFractionSeconds() {
cal.set(Calendar.MILLISECOND,parseInt(1,3));
skipDigits();
}
protected void setTimeZone( java.util.TimeZone tz ) {
cal.setTimeZone(tz);
}
protected void setSeconds(int i) {
cal.set(Calendar.SECOND,i);
}
protected void setMinutes(int i) {
cal.set(Calendar.MINUTE,i);
}
protected void setHours(int i) {
cal.set(Calendar.HOUR_OF_DAY,i);
}
protected void setDay(int i) {
cal.set(Calendar.DAY_OF_MONTH,i);
}
protected void setMonth(int i) {
cal.set(Calendar.MONTH,i-1); // month is 0-origin.
}
protected void setYear(int i) {
cal.set(Calendar.YEAR,i);
}
} msv-2009.1/xsdlib/src/com/sun/msv/datatype/xsd/datetime/BigTimeDurationValueType.java 0000644 0001750 0001750 00000031766 10223102562 031027 0 ustar giovanni giovanni /*
* @(#)$Id: BigTimeDurationValueType.java 1650 2005-03-31 23:19:14Z kohsuke $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.msv.datatype.xsd.datetime;
import com.sun.msv.datatype.xsd.Comparator;
import java.io.IOException;
import java.io.ObjectInputStream;
import java.math.BigDecimal;
import java.math.BigInteger;
/**
* ITimeDurationValueType implementation that can hold all lexically legal
* timeDuration value.
*
* @author Kohsuke KAWAGUCHI
*/
public class BigTimeDurationValueType implements ITimeDurationValueType {
protected int signum;
// all the fields should be positive
protected BigInteger year;
protected BigInteger month;
protected BigInteger day;
protected BigInteger hour;
protected BigInteger minute;
protected BigDecimal second;
private static final BigDateTimeValueType[] testInstance =
new BigDateTimeValueType[]{
new BigDateTimeValueType(
new BigInteger("1696"), 8/*Sep*/, 0/*1st*/, 0,0, new BigDecimal(0), TimeZone.ZERO ),
new BigDateTimeValueType(
new BigInteger("1697"), 1/*Feb*/, 0/*1st*/, 0,0, new BigDecimal(0), TimeZone.ZERO ),
new BigDateTimeValueType(
new BigInteger("1903"), 2/*Mar*/, 0/*1st*/, 0,0, new BigDecimal(0), TimeZone.ZERO ),
new BigDateTimeValueType(
new BigInteger("1903"), 6/*Jul*/, 0/*1st*/, 0,0, new BigDecimal(0), TimeZone.ZERO ) };
public boolean equals(Object o) {
return equals((ITimeDurationValueType)o);
}
public boolean equals(ITimeDurationValueType o) {
return compare(o) == Comparator.EQUAL;
}
public String toString() {
return (signum<0?"-":"")+
"P"+nullAsZero(year).abs()+"Y"+
nullAsZero(month)+"M"+
nullAsZero(day)+"DT"+
nullAsZero(hour)+"H"+
nullAsZero(minute)+"M"+
(second==null?"":second.toString())+"S";
}
private BigInteger nullAsZero(BigInteger o) {
if (o == null)
return BigInteger.ZERO;
else
return o;
}
/**
* hash code has to be consistent with equals method.
*/
public int hashCode() {
// 400Y = 365D*303 + 366D*97 = 146097D = 3506328 hours
// = 210379680 minutes
// and no other smaller years have their equivalent days.
// hashCode is very complex because it has to consistent with the behavior of equals method.
return nullAsZero(day)
.multiply(Util.the24)
.add(nullAsZero(hour))
.multiply(Util.the60)
.add(nullAsZero(minute))
.mod(Util.the210379680)
.hashCode();
}
public int compare(ITimeDurationValueType o) {
if (!(o instanceof BigTimeDurationValueType))
o = o.getBigValue();
return compare(this, (BigTimeDurationValueType)o);
}
static private int compare(BigTimeDurationValueType lhs, BigTimeDurationValueType rhs) {
boolean less = false, greater = false, noDeterminate = false;
for (int i = 0; i < testInstance.length; i++) {
BigDateTimeValueType l = (BigDateTimeValueType)testInstance[i].add(lhs);
BigDateTimeValueType r = (BigDateTimeValueType)testInstance[i].add(rhs);
int v = BigDateTimeValueType.compare(l, r);
if (v < 0)
less = true;
if (v > 0)
greater = true;
if (v == 0) {
if (!l.equals(r))
noDeterminate = true;
}
}
if (noDeterminate)
return Comparator.UNDECIDABLE;
if (less && greater)
return Comparator.UNDECIDABLE;
if (less)
return Comparator.LESS; // lhsrhs
return Comparator.EQUAL;
}
public BigTimeDurationValueType getBigValue() { return this; }
/**
* All the fields should be positive and use the signum field to
* determine the sign.
*/
public BigTimeDurationValueType(
int signum,
BigInteger year, BigInteger month, BigInteger day,
BigInteger hour, BigInteger minute, BigDecimal second ) {
this.signum = signum;
this.year = year!=null?year:BigInteger.ZERO;
this.month = month!=null?month:BigInteger.ZERO;
this.day = day!=null?day:BigInteger.ZERO;
this.hour = hour!=null?hour:BigInteger.ZERO;
this.minute = minute!=null?minute:BigInteger.ZERO;
this.second = second!=null?second:Util.decimal0;
}
public static BigTimeDurationValueType fromMinutes( int minutes )
{ return fromMinutes(Util.int2bi(minutes)); }
public static BigTimeDurationValueType fromMinutes( BigInteger minutes )
{ return new BigTimeDurationValueType(minutes.signum(),null,null,null,null,minutes.abs(),null); }
/**
* @return non-null positive value. use {@link #signum} for the sign.
*/
public BigInteger getDay() {
return day;
}
/**
* @return non-null positive value. use {@link #signum} for the sign.
*/
public BigInteger getHour() {
return hour;
}
/**
* @return non-null positive value. use {@link #signum} for the sign.
*/
public BigInteger getMinute() {
return minute;
}
/**
* @return non-null positive value. use {@link #signum} for the sign.
*/
public BigInteger getMonth() {
return month;
}
/**
* @return non-null positive value. use {@link #signum} for the sign.
*/
public BigDecimal getSecond() {
return second;
}
/**
* @return non-null positive value. use {@link #signum} for the sign.
*/
public BigInteger getYear() {
return year;
}
/**
* Reads in the lexical duration format.
*
* @param lexicalRepresentation
* whitespace stripped lexical form.
*/
public BigTimeDurationValueType(String lexicalRepresentation) throws IllegalArgumentException {
final String s = lexicalRepresentation;
int[] idx = new int[1];
boolean positive;
if (s.charAt(idx[0]) == '-') {
idx[0]++;
positive = false;
} else {
positive = true;
}
if (s.charAt(idx[0]++) != 'P') {
throw new IllegalArgumentException(s); //,idx[0]-1);
}
// phase 1: chop the string into chunks
// (where a chunk is ''
//--------------------------------------
int dateLen = 0;
String[] dateParts = new String[3];
int[] datePartsIndex = new int[3];
while (s.length() != idx[0]
&& isDigit(s.charAt(idx[0]))
&& dateLen < 3) {
datePartsIndex[dateLen] = idx[0];
dateParts[dateLen++] = parsePiece(s, idx);
}
if (s.length() != idx[0] && s.charAt(idx[0]++) != 'T') {
throw new IllegalArgumentException(s); // ,idx[0]-1);
}
int timeLen = 0;
String[] timeParts = new String[3];
int[] timePartsIndex = new int[3];
while (s.length() != idx[0]
&& isDigitOrPeriod(s.charAt(idx[0]))
&& timeLen < 3) {
timePartsIndex[timeLen] = idx[0];
timeParts[timeLen++] = parsePiece(s, idx);
}
if (s.length() != idx[0]) {
throw new IllegalArgumentException(s); // ,idx[0]);
}
if (dateLen == 0 && timeLen == 0) {
throw new IllegalArgumentException(s); // ,idx[0]);
}
// phase 2: check the ordering of chunks
//--------------------------------------
organizeParts(s, dateParts, datePartsIndex, dateLen, "YMD");
organizeParts(s, timeParts, timePartsIndex, timeLen, "HMS");
// parse into numbers
year = parseBigInteger(s, dateParts[0], datePartsIndex[0]);
month = parseBigInteger(s, dateParts[1], datePartsIndex[1]);
day = parseBigInteger(s, dateParts[2], datePartsIndex[2]);
hour = parseBigInteger(s, timeParts[0], timePartsIndex[0]);
minute = parseBigInteger(s, timeParts[1], timePartsIndex[1]);
second = parseBigDecimal(s, timeParts[2], timePartsIndex[2]);
// null -> 0
year = year!=null?year:BigInteger.ZERO;
month = month!=null?month:BigInteger.ZERO;
day = day!=null?day:BigInteger.ZERO;
hour = hour!=null?hour:BigInteger.ZERO;
minute = minute!=null?minute:BigInteger.ZERO;
second = second!=null?second:Util.decimal0;
if( getSignum(year)==0 && getSignum(month)==0 && getSignum(day)==0
&& getSignum(hour)==0 && getSignum(minute)==0 && getSignum(second)==0) {
signum = 0;
} else
if (positive) {
signum = 1;
} else {
signum = -1;
}
}
private int getSignum( BigInteger i ) {
if( i == null ) return 0;
else return i.signum();
}
private int getSignum( BigDecimal i ) {
if( i == null ) return 0;
else return i.signum();
}
private static boolean isDigit(char ch) {
return '0' <= ch && ch <= '9';
}
private static boolean isDigitOrPeriod(char ch) {
return isDigit(ch) || ch == '.';
}
private static String parsePiece(String whole, int[] idx) throws IllegalArgumentException {
int start = idx[0];
while (idx[0] < whole.length()
&& isDigitOrPeriod(whole.charAt(idx[0]))) {
idx[0]++;
}
if (idx[0] == whole.length()) {
throw new IllegalArgumentException(whole); // ,idx[0]);
}
idx[0]++;
return whole.substring(start, idx[0]);
}
private static void organizeParts( String whole, String[] parts,
int[] partsIndex, int len, String tokens)
throws IllegalArgumentException {
int idx = tokens.length();
for (int i = len - 1; i >= 0; i--) {
int nidx =
tokens.lastIndexOf(
parts[i].charAt(parts[i].length() - 1),
idx - 1);
if (nidx == -1) {
throw new IllegalArgumentException(whole);
// ,partsIndex[i]+parts[i].length()-1);
}
for (int j = nidx + 1; j < idx; j++) {
parts[j] = null;
}
idx = nidx;
parts[idx] = parts[i];
partsIndex[idx] = partsIndex[i];
}
for (idx--; idx >= 0; idx--) {
parts[idx] = null;
}
}
private static BigInteger parseBigInteger( String whole, String part, int index) throws IllegalArgumentException {
if (part == null) {
return null;
}
part = part.substring(0, part.length() - 1);
// syntax error will cause NumberFormatException, which is IllegalArgumentException
return new BigInteger(part);
}
private static BigDecimal parseBigDecimal( String whole, String part, int index) throws IllegalArgumentException {
if (part == null) {
return null;
}
part = part.substring(0, part.length() - 1);
// syntax error will cause NumberFormatException, which is IllegalArgumentException
return new BigDecimal(part);
}
// serialization support
private static final long serialVersionUID = 1;
private void readObject( ObjectInputStream ois ) throws IOException, ClassNotFoundException {
ois.defaultReadObject();
// read in the old format where there was no signum field
// and the most significant field was carrying the sign.
switch( year.signum() ) {
case -1: signum=-1; year=year.negate(); return;
case 1: signum= 1; return;
}
switch( month.signum() ) {
case -1: signum=-1; month=month.negate(); return;
case 1: signum= 1; return;
}
switch( day.signum() ) {
case -1: signum=-1; day=day.negate(); return;
case 1: signum= 1; return;
}
switch( hour.signum() ) {
case -1: signum=-1; hour=hour.negate(); return;
case 1: signum= 1; return;
}
switch( minute.signum() ) {
case -1: signum=-1; minute=minute.negate(); return;
case 1: signum= 1; return;
}
switch( second.signum() ) {
case -1: signum=-1; second=second.negate(); return;
case 1: signum= 1; return;
}
signum = 0;
}
}
msv-2009.1/xsdlib/src/com/sun/msv/datatype/xsd/datetime/CalendarFormatter.java 0000644 0001750 0001750 00000004611 07767675635 027567 0 ustar giovanni giovanni /*
* @(#)$Id: CalendarFormatter.java 1623 2003-12-16 21:39:41Z kohsuke $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.msv.datatype.xsd.datetime;
import java.util.Calendar;
/**
* Formats a {@link Calendar} object to a String.
*
* @author
* Kohsuke Kawaguchi (kohsuke.kawaguchi@sun.com)
*/
public final class CalendarFormatter extends AbstractCalendarFormatter {
private CalendarFormatter() {} // no instanciation
private static final CalendarFormatter theInstance = new CalendarFormatter();
public static String format( String format, Calendar cal ) {
return theInstance.doFormat(format,cal);
}
protected Calendar toCalendar(Object cal) {
return (Calendar)cal;
}
protected void formatYear(Object cal, StringBuffer buf) {
int year = ((Calendar)cal).get(Calendar.YEAR);
String s;
if (year <= 0) // negative value
s = Integer.toString(1 - year);
else // positive value
s = Integer.toString(year);
while (s.length() < 4)
s = "0" + s;
if (year <= 0)
s = "-" + s;
buf.append(s);
}
protected void formatMonth(Object cal, StringBuffer buf) {
formatTwoDigits(((Calendar)cal).get(Calendar.MONTH)+1,buf);
}
protected void formatDays(Object cal, StringBuffer buf) {
formatTwoDigits(((Calendar)cal).get(Calendar.DAY_OF_MONTH),buf);
}
protected void formatHours(Object cal, StringBuffer buf) {
formatTwoDigits(((Calendar)cal).get(Calendar.HOUR_OF_DAY),buf);
}
protected void formatMinutes(Object cal, StringBuffer buf) {
formatTwoDigits(((Calendar)cal).get(Calendar.MINUTE),buf);
}
protected void formatSeconds(Object _cal, StringBuffer buf) {
Calendar cal = (Calendar)_cal;
formatTwoDigits(cal.get(Calendar.SECOND),buf);
if (cal.isSet(Calendar.MILLISECOND)) { // milliseconds
int n = cal.get(Calendar.MILLISECOND);
if(n!=0) {
String ms = Integer.toString(n);
while (ms.length() < 3)
ms = "0" + ms; // left 0 paddings.
buf.append('.');
buf.append(ms);
}
}
}
}
msv-2009.1/xsdlib/src/com/sun/msv/datatype/xsd/datetime/DateTimeFactory.java 0000644 0001750 0001750 00000003546 07767675635 027224 0 ustar giovanni giovanni /*
* @(#)$Id: DateTimeFactory.java 1623 2003-12-16 21:39:41Z kohsuke $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.msv.datatype.xsd.datetime;
import java.math.BigDecimal;
import java.math.BigInteger;
/**
* utility functions that creates date/time related objects.
*
* @author Kohsuke KAWAGUCHI
*/
public class DateTimeFactory {
public static IDateTimeValueType createFromDateTime(
Number year, Integer month, Integer day,
Integer hour, Integer minute, Number mSecond, java.util.TimeZone zone ) {
// if( year instanceof Integer )
// return new SmallDateTimeValueType( ... );
BigDecimal second=null;
if( year instanceof Integer ) year = new BigInteger(year.toString());
if( mSecond!=null ) {
if( mSecond instanceof Integer ) // convert it to second
second = new BigDecimal(mSecond.toString()).movePointLeft(3);
else
if( mSecond instanceof BigDecimal )
second = ((BigDecimal)mSecond).movePointLeft(3);
else
throw new UnsupportedOperationException();
}
return new BigDateTimeValueType( (BigInteger)year, month, day, hour, minute, second, zone );
}
public static IDateTimeValueType createFromDate(
Number year, Integer month, Integer day, java.util.TimeZone zone ) {
return createFromDateTime( year, month, day, null, null, null, zone );
}
public static IDateTimeValueType createFromTime(
Integer hour, Integer minute, Number mSecond, java.util.TimeZone zone ) {
return createFromDateTime( null, null, null, hour, minute, mSecond, zone );
}
}
msv-2009.1/xsdlib/src/com/sun/msv/datatype/xsd/datetime/BigDateTimeValueType.java 0000644 0001750 0001750 00000040416 10223102562 030107 0 ustar giovanni giovanni /*
* @(#)$Id: BigDateTimeValueType.java 1650 2005-03-31 23:19:14Z kohsuke $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.msv.datatype.xsd.datetime;
import com.sun.msv.datatype.xsd.Comparator;
import java.math.BigDecimal;
import java.math.BigInteger;
import java.util.Calendar;
/**
* DateTimeValueType object that can hold all lexically valid dateTime value.
*
* This class provides:
*
*
.
* See http://www.w3.org/TR/xmlschema-2/#NMTOKEN for the spec
*
* @author Kohsuke KAWAGUCHI
*/
public class NmtokenType extends TokenType {
public static final NmtokenType theInstance = new NmtokenType("NMTOKEN");
protected NmtokenType(String typeName) { super(typeName,false); }
final public XSDatatype getBaseType() {
return TokenType.theInstance;
}
public Object _createValue( String content, ValidationContext context ) {
if(XmlNames.isNmtoken(content)) return content;
else return null;
}
// serialization support
private static final long serialVersionUID = 1;
}
msv-2009.1/xsdlib/src/com/sun/msv/datatype/xsd/IntegerValueType.java 0000644 0001750 0001750 00000014364 07671171415 025615 0 ustar giovanni giovanni /*
* @(#)$Id: IntegerValueType.java 1567 2003-06-09 20:50:21Z kk122374 $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.msv.datatype.xsd;
import java.math.BigInteger;
/**
* Value object of "integer" type.
*
* @author Kohsuke KAWAGUCHI
*/
public class IntegerValueType extends Number implements Comparable, java.io.Serializable {
/** canonical representation of absolute value of integer
*
* BNF of canonical representation
*
* canonical_integer := "0" | nonzero
* nonzero := '-'? ["1"-"9"] ["0"-"9"]*
*/
private final String value;
/** internal use only: construct object from canonicalized value */
private IntegerValueType(String canonicalizedValue) {
value = canonicalizedValue;
}
private IntegerValueType( long v ) {
this.value = Long.toString(v);
}
/**
* translates a BigInteger to an IntegerValueType.
*/
public static IntegerValueType create(BigInteger bi) {
return create(bi.toString());
}
/**
* translates non-canonicalized representation of an integer into
* an IntegerValueType.
*
* @return null
* when the parameter is not even valid with respect to
* the lexical space of "integer" type specified in
* XML Schema datatype spec.
*/
public static IntegerValueType create(String nonCanonicalizedValue) {
int idx = 0;
String v = "";
final int len = nonCanonicalizedValue.length();
if (len == 0)
return null;
switch (nonCanonicalizedValue.charAt(idx)) {
case '+' :
idx++;
break; // ignore the sign
case '-' :
v += '-';
idx++;
break;
case '0' :
case '1' :
case '2' :
case '3' :
case '4' :
case '5' :
case '6' :
case '7' :
case '8' :
case '9' :
break;
default :
return null;
}
if (idx == len)
return null; // just sign only: reject it
// skip leading '0'
while (idx < len && nonCanonicalizedValue.charAt(idx) == '0')
idx++;
if (idx == len) {
// all the digits are skipped : that means this value is 0
return new IntegerValueType("0");
}
// adding digits
while (idx < len) {
final char ch = nonCanonicalizedValue.charAt(idx++);
if ('0' <= ch && ch <= '9')
v += ch;
else
return null; // illegal char
}
return new IntegerValueType(v);
}
/**
* @return 1 if this value is bigger than rhs
* 0 if the values are the same
* -1 if rhs is bigger than this.
*/
public int compareTo(Object o) {
IntegerValueType rhs;
if (o instanceof IntegerValueType)
rhs = (IntegerValueType)o;
else
rhs = new IntegerValueType(((Number)o).longValue());
boolean lhsIsNegative = value.charAt(0) == '-';
boolean rhsIsNegative = rhs.value.charAt(0) == '-';
if (lhsIsNegative && !rhsIsNegative)
return -1;
if (rhsIsNegative && !lhsIsNegative)
return 1;
// now both number have the same sign.
int lp, rp, llen, rlen;
if (lhsIsNegative && rhsIsNegative)
lp = rp = 1;
else
lp = rp = 0;
llen = value.length() - lp;
rlen = rhs.value.length() - rp;
if (llen > rlen)
return lhsIsNegative ? -1 : 1;
if (llen < rlen)
return lhsIsNegative ? 1 : -1;
// now we have the same length. compare left to right
while (llen > 0) {
final char lch = value.charAt(lp++);
final char rch = rhs.value.charAt(rp++);
if (lch > rch)
return lhsIsNegative ? -1 : 1;
if (lch < rch)
return lhsIsNegative ? 1 : -1;
llen--;
}
return 0; // they are the same value
}
public boolean equals(Object o) {
if (o instanceof IntegerValueType)
return value.equals(((IntegerValueType)o).value);
else
return false;
}
public int hashCode() {
return value.hashCode();
}
public String toString() {
return value;
}
public int precision() {
// TODO : what is the exact definition of "precision"?
// What is the precision of "100"? 1, or 3?
final int len = value.length();
if (value.charAt(0) == '-')
return len - 1;
else
return len;
}
/** returns true if the value if non-positive (less than or equal to zero) */
public boolean isNonPositive() {
final char ch = value.charAt(0);
if (ch == '-' || ch == '0')
return true;
return false;
}
/** returns true if the value if positive (greater than zero) */
public boolean isPositive() {
final char ch = value.charAt(0);
if (ch == '-' || ch == '0')
return false;
return true;
}
/** returns true if the value if negative (less than zero) */
public boolean isNegative() {
return value.charAt(0) == '-';
}
/** returns true if the value if non-negative (greater than or equal to zero) */
public boolean isNonNegative() {
return value.charAt(0) != '-';
}
/** converts to BigInteger. */
public BigInteger toBigInteger() {
return new BigInteger(value);
}
public double doubleValue() {
return toBigInteger().doubleValue();
}
public float floatValue() {
return (float)doubleValue();
}
public int intValue() {
return toBigInteger().intValue();
}
public long longValue() {
return toBigInteger().longValue();
}
// serialization support
private static final long serialVersionUID = 1;
}
msv-2009.1/xsdlib/src/com/sun/msv/datatype/xsd/DataTypeWithValueConstraintFacet.java 0000644 0001750 0001750 00000002273 07671171415 030731 0 ustar giovanni giovanni /*
* @(#)$Id: DataTypeWithValueConstraintFacet.java 1567 2003-06-09 20:50:21Z kk122374 $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.msv.datatype.xsd;
import org.relaxng.datatype.DatatypeException;
import org.relaxng.datatype.ValidationContext;
/**
* base class for facets which constrain value space.
*
* @author Kohsuke KAWAGUCHI
*/
abstract class DataTypeWithValueConstraintFacet extends DataTypeWithFacet {
DataTypeWithValueConstraintFacet(
String nsUri, String typeName, XSDatatypeImpl baseType, String facetName, boolean _isFixed )
throws DatatypeException {
super( nsUri, typeName, baseType, facetName, _isFixed );
}
final protected boolean needValueCheck() { return true; }
protected final boolean checkFormat( String literal, ValidationContext context ) {
return _createValue(literal,context)!=null;
}
// serialization support
private final static long serialVersionUID = 2497055158497151572L;
}
msv-2009.1/xsdlib/src/com/sun/msv/datatype/xsd/TokenType.java 0000644 0001750 0001750 00000001730 07671171415 024274 0 ustar giovanni giovanni /*
* @(#)$Id: TokenType.java 1567 2003-06-09 20:50:21Z kk122374 $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.msv.datatype.xsd;
/**
* "token" type.
*
* type of the value object is java.lang.String.
* See http://www.w3.org/TR/xmlschema-2/#token for the spec
*
* @author Kohsuke KAWAGUCHI
*/
public class TokenType extends StringType {
public static final TokenType theInstance = new TokenType("token",true);
protected TokenType( String typeName, boolean isAlwaysValid ) {
super(typeName,WhiteSpaceProcessor.theCollapse,isAlwaysValid);
}
public XSDatatype getBaseType() {
return NormalizedStringType.theInstance;
}
// serialization support
private static final long serialVersionUID = 1;
}
msv-2009.1/xsdlib/src/com/sun/msv/datatype/xsd/EnumerationFacet.java 0000644 0001750 0001750 00000004640 10223102562 025566 0 ustar giovanni giovanni /*
* @(#)$Id: EnumerationFacet.java 1650 2005-03-31 23:19:14Z kohsuke $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.msv.datatype.xsd;
import org.relaxng.datatype.DatatypeException;
import org.relaxng.datatype.ValidationContext;
import java.util.Collection;
import java.util.Set;
/**
* "enumeration" facets validator.
*
* @author Kohsuke KAWAGUCHI
*/
public class EnumerationFacet extends DataTypeWithValueConstraintFacet {
protected EnumerationFacet( String nsUri, String typeName, XSDatatypeImpl baseType, Collection _values, boolean _isFixed )
throws DatatypeException {
super(nsUri,typeName,baseType,FACET_ENUMERATION,_isFixed);
values = new java.util.HashSet( _values );
}
/** set of valid values */
public final Set values;
public Object _createValue( String literal, ValidationContext context ) {
Object o = baseType._createValue(literal,context);
if(o==null || !values.contains(o)) return null;
return o;
}
protected void diagnoseByFacet(String content, ValidationContext context) throws DatatypeException {
if( _createValue(content,context)!=null ) return;
// TODO: guess which item the user was trying to specify
if( values.size()<=4 ) {
// if choices are small in number, include them into error messages.
Object[] members = values.toArray();
String r="";
if( members[0] instanceof String
|| members[0] instanceof Number ) {
// this will cover 80% of the use case.
r += "\""+members[0].toString()+"\"";
for( int i=1; ijava.lang.Integer.
* See http://www.w3.org/TR/xmlschema-2/#unsignedShort for the spec
*
* We don't have language support for unsigned datatypes, so things are not so easy.
* UnsignedShortType uses a IntType as a base implementation, for the convenience and
* faster performance.
*
* @author Kohsuke KAWAGUCHI
*/
public class UnsignedShortType extends IntType {
public static final UnsignedShortType theInstance = new UnsignedShortType();
private UnsignedShortType() {
super("unsignedShort",createRangeFacet(
UnsignedIntType.theInstance,
null,
new Integer(65535)));
}
public XSDatatype getBaseType() {
return UnsignedIntType.theInstance;
}
/** upper bound value. this is the maximum possible valid value as an unsigned int */
private static final int upperBound = 65535;
public Object _createValue( String lexicalValue, ValidationContext context ) {
// Implementation of JDK1.2.2/JDK1.3 is suitable enough
try {
Integer v = (Integer)super._createValue(lexicalValue,context);
if(v==null) return null;
if( v.intValue()<0 ) return null;
if( v.intValue()>upperBound ) return null;
return v;
} catch( NumberFormatException e ) {
return null;
}
}
// serialization support
private static final long serialVersionUID = 1;
}
msv-2009.1/xsdlib/src/com/sun/msv/datatype/xsd/QnameValueType.java 0000644 0001750 0001750 00000002333 10466717621 025253 0 ustar giovanni giovanni /*
* @(#)$Id: QnameValueType.java 1718 2006-08-10 21:05:21Z kohsuke $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.msv.datatype.xsd;
/** value object of QName.
*
* @author Kohsuke KAWAGUCHI
*/
public class QnameValueType implements java.io.Serializable {
public final String namespaceURI;
public final String localPart;
public boolean equals( Object o ) {
if(o==null || !(o instanceof QnameValueType)) return false;
QnameValueType rhs = (QnameValueType)o;
return namespaceURI.equals(rhs.namespaceURI) && localPart.equals(rhs.localPart);
}
public int hashCode() {
return namespaceURI.hashCode()+localPart.hashCode();
}
public String toString() {
return "{"+namespaceURI+"}:"+localPart;
}
public QnameValueType( String uri, String localPart ) {
this.namespaceURI = uri;
this.localPart = localPart;
}
// serialization support
private static final long serialVersionUID = 1;
}
msv-2009.1/xsdlib/src/com/sun/msv/datatype/xsd/FractionDigitsFacet.java 0000644 0001750 0001750 00000005551 07671171415 026233 0 ustar giovanni giovanni /*
* @(#)$Id: FractionDigitsFacet.java 1567 2003-06-09 20:50:21Z kk122374 $
*
* Copyright 2001 Sun Microsystems, Inc. All Rights Reserved.
*
* This software is the proprietary information of Sun Microsystems, Inc.
* Use is subject to license terms.
*
*/
package com.sun.msv.datatype.xsd;
import org.relaxng.datatype.DatatypeException;
import org.relaxng.datatype.ValidationContext;
/**
* 'fractionDigits' facet.
*
* this class holds these facet information and performs validation.
*
* @author Kohsuke KAWAGUCHI
*/
public class FractionDigitsFacet extends DataTypeWithLexicalConstraintFacet {
/** maximum number of fraction digits */
public final int scale;
public FractionDigitsFacet( String nsUri, String typeName, XSDatatypeImpl baseType, int _scale, boolean _isFixed )
throws DatatypeException {
super( nsUri, typeName, baseType, FACET_FRACTIONDIGITS, _isFixed );
scale = _scale;
// loosened facet check
DataTypeWithFacet o = baseType.getFacetObject(FACET_FRACTIONDIGITS);
if(o!=null && ((FractionDigitsFacet)o).scale < this.scale )
throw new DatatypeException( localize( ERR_LOOSENED_FACET,
FACET_FRACTIONDIGITS, o.displayName() ) );
// consistency with precision is checked in XSDatatypeImpl.derive method.
}
protected boolean checkLexicalConstraint( String content ) {
return countScale(content)<=scale;
}
protected void diagnoseByFacet(String content, ValidationContext context) throws DatatypeException {
final int cnt = countScale(content);
if(cnt<=scale) return;
throw new DatatypeException( DatatypeException.UNKNOWN,
localize(ERR_TOO_MUCH_SCALE,
new Integer(cnt), new Integer(scale)) );
}
/** count the number of fractional digits.
*
* this method can assume that the given literal is appropriate
* as an decimal value.
*
* "the number of fractional digits" is defined in
* http://www.w3.org/TR/xmlschema-2/#number
*/
final protected static int countScale( String literal ) {
final int len = literal.length();
boolean skipMode = true;
int count=0;
int trailingZero=0;
for( int i=0; i
W3C XML Schema Datatypes implementation.
This package implements the recommendation version of W3C XML Schema Part 2 datatypes.
The latest version of the spec is here.
Application developers should understand the usage of
the following classes:
com.sun.msv.datatype.xsd.DatatypeFactory,
com.sun.msv.datatype.xsd.XSDatatype,
org.relaxng.datatype.Datatype, and
org.relaxng.datatype.ValidationContext.
Other classes are implementations of those types and therefore not important in most cases.
The current release has several limitations. See readme.txt for details.
For types derived by list, the createJavaObject method returns java.lang.Object[]
that contains Java values of the item type.
For types derived by restriction, the method returns the same type as the base type.
For types derived by union, the method returns Java values of one of the member types.
The createJavaObject method currently returns meaningless types for
"duration" datatype.
*1
The first item in the array is the namespace URI. The second (the last) item in the array is
the local name.
*2
Missing fields are not set. For example, "gYearMonth" type returns
a Calendar object whose DAY_OF_MONTH, HOUR_OF_DAY, MINUTE,SECOND, and
MILLISECOND fields are not set.
If the XML representation does not contain the millisecond part,
then MILLISECOND field of the returned Calendar object
is not set. This field is set only when the XML representation contains
fractional seconds (e.g., "01:02:03.5").
*3
The anyURI type does not perform URI escaping. So it returns "%20" for
the lexical value "%20".
*4
The language type always return a string in the lower case. That is,
it returns "en_us" for "EN_US".
*5
Strings are white-space normalized according to the value of
the whiteSpace facet. For example, " abc " as a Name yields "abc";
" abc " as a string yields " abc ".